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

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “terms,” especially when it appears in the phrase “in terms of.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Face
    -0.07
     NumberOf
    -0.07
     deaths
    -0.06
    /T
    -0.06
    "L
    -0.06
    (round
    -0.06
    Interaction
    -0.06
    "S
    -0.06
    _WORD
    -0.06
     Meat
    -0.06
    POSITIVE LOGITS
    cede
    0.07
    acock
    0.07
    elaide
    0.07
     пері
    0.07
     plá
    0.06
     slog
    0.06
    ecess
    0.06
    (ident
    0.06
     الكه
    0.06
    スレ
    0.06
    Act Density 0.030%

    No Known Activations