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

    Neuronpedia

    INDEX
    Explanations

    directory level up

    np_max-act · gemini-2.0-flash

    file operation commands in a shell environment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .window
    -0.07
     concludes
    -0.07
    -ID
    -0.06
     Lab
    -0.06
    Thin
    -0.06
     Patron
    -0.06
     counted
    -0.06
     sacred
    -0.06
    -sided
    -0.06
    —with
    -0.06
    POSITIVE LOGITS
    compress
    0.07
     ;↵
    0.07
     toReturn
    0.06
     jov
    0.06
    Sat
    0.06
    _uniform
    0.06
    _pause
    0.06
    edik
    0.06
     werk
    0.06
    :'/
    0.06
    Act Density 0.009%

    No Known Activations