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

    Neuronpedia

    INDEX
    Explanations

    Coding problems/solutions

    np_max-act · gemini-2.0-flash

    complex technical processes related to manufacturing or materials science.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron lights up on tokens from the author’s solution‐explanation section (e.g. the “EDIT: I’ve solved… by…” part of a Q&A answer).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    рут
    -0.07
    اسية
    -0.06
    legt
    -0.06
    GLOBALS
    -0.06
    辛
    -0.06
    اب
    -0.06
    _activation
    -0.06
    zers
    -0.06
     Takes
    -0.06
    09
    -0.06
    POSITIVE LOGITS
    _rep
    0.07
    __).
    0.07
     bohat
    0.06
     //////////////////////////////////
    0.06
     ofType
    0.06
    Opaque
    0.06
     TokenType
    0.06
     сфер
    0.06
    mA
    0.06
    .gwt
    0.06
    Act Density 0.089%

    No Known Activations