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

    Neuronpedia

    INDEX
    Explanations

    positive social endorsements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    There
    0.79
    t
    0.78
    It
    0.74
     It
    0.73
    N
    0.73
    ด
    0.70
    '
    0.69
     There
    0.66
    %
    0.66
    What
    0.64
    POSITIVE LOGITS
    adı
    0.79
    ເພື່ອ
    0.77
    ностей
    0.77
     sixties
    0.75
    apeti
    0.74
    amano
    0.74
    umim
    0.74
    ală
    0.72
    ayutt
    0.72
    ější
    0.71
    Act Density 0.001%

    No Known Activations