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

    Neuronpedia

    INDEX
    Explanations

    .W

    np_max-act · gemini-2.0-flash

    The neuron fires on parts of legal case citations—specifically the “S.W.” reporter abbreviation (and its accompanying volume numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ooo
    -0.06
    esus
    -0.06
     Coming
    -0.06
     marched
    -0.06
    ترك
    -0.06
    nuts
    -0.06
    üsü
    -0.06
    asics
    -0.06
    ité
    -0.06
    iniz
    -0.06
    POSITIVE LOGITS
    /*/
    0.07
     पढ़
    0.07
    whereIn
    0.07
     Vick
    0.07
    ($)
    0.06
     λι
    0.06
    (sz
    0.06
     [...]
    0.06
    .lineWidth
    0.06
    estar
    0.06
    Act Density 0.000%

    No Known Activations