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

    Neuronpedia

    INDEX
    Explanations

    people, advice, or specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    各地
    2.91
    malign
    2.86
     temprana
    2.83
     disput
    2.81
     erstmal
    2.78
     GÉN
    2.76
    剤
    2.76
    mış
    2.75
    हट
    2.73
     hearsay
    2.73
    POSITIVE LOGITS
    pection
    2.90
    واری
    2.75
     parseInt
    2.71
    arded
    2.66
    داران
    2.63
    uot
    2.61
    iovascular
    2.59
    程式
    2.53
    '$
    2.53
    as
    2.51
    Act Density 0.008%

    No Known Activations