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

    Neuronpedia

    INDEX
    Explanations

    AI models/code

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “model,” i.e. self-references to the AI model.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Щ
    -0.07
    ãi
    -0.07
     مدیر
    -0.07
    ัดส
    -0.07
     закры
    -0.07
    ुब
    -0.06
    ِ
    -0.06
    Vo
    -0.06
     deren
    -0.06
     Lê
    -0.06
    POSITIVE LOGITS
    ,size
    0.07
    _INTERFACE
    0.07
    .yahoo
    0.06
     influence
    0.06
    commons
    0.06
    .databind
    0.06
    BUM
    0.06
    .sat
    0.06
    -development
    0.06
    (QtGui
    0.06
    Act Density 0.005%

    No Known Activations