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

    Neuronpedia

    INDEX
    Explanations

    now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Remedies
    0.71
    рыва
    0.70
    стры
    0.69
    кера
    0.69
    me
    0.68
    ます
    0.68
    лэ
    0.68
     Hurry
    0.68
    ありません
    0.67
    ない
    0.67
    POSITIVE LOGITS
     meaty
    0.81
    TimeStamp
    0.79
    Lapangan
    0.79
    Ƙ
    0.79
    િમ
    0.79
    赟
    0.79
     时
    0.77
    द्दीन
    0.77
    叧
    0.77
     designers
    0.75
    Act Density 0.000%

    No Known Activations