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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on negative evaluative words or phrases (criticism), such as “bad,” “wrong,” or other judgments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ObjectId
    -0.06
    .Template
    -0.06
    λλ
    -0.06
    nerRadius
    -0.06
    defaultValue
    -0.06
     نزد
    -0.06
    nod
    -0.06
    .ref
    -0.06
     TForm
    -0.06
    _low
    -0.06
    POSITIVE LOGITS
     �
    0.07
     hometown
    0.07
    .Small
    0.06
     unc
    0.06
     coupons
    0.06
    cnt
    0.06
    mile
    0.06
    _cols
    0.06
     BA
    0.06
     ticker
    0.06
    Act Density 0.025%

    No Known Activations