Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron fires on technical action words and procedure names—whether they’re verbs in job-responsibility statements (e.g. “completing,” “establishing,” “researching”) or identifiers and file names in code (e.g. “types.h,” “error,” “initialize”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to job titles and professional roles.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Fill
    -0.06
    //-
    -0.06
    .*↵↵
    -0.06
     المست
    -0.06
    ################################################################################
    -0.06
     excer
    -0.06
    .Find
    -0.06
    translated
    -0.06
    (parsed
    -0.06
     경우
    -0.06
    POSITIVE LOGITS
     Insert
    0.06
     Cavs
    0.06
    s
    0.06
    _UPLOAD
    0.06
    VERTISE
    0.06
     Dragon
    0.06
    \Models
    0.06
    oundary
    0.06
    .getLocal
    0.06
     inflamm
    0.06
    Act Density 0.043%

    No Known Activations