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

    Neuronpedia

    INDEX
    Explanations

    Towards Data Science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cedented
    0.67
    keyed
    0.57
    orted
    0.54
    ,"
    0.54
    versed
    0.53
    opened
    0.52
    Nor
    0.52
    s
    0.51
    Op
    0.51
    P
    0.51
    POSITIVE LOGITS
     Badge
    0.77
     শুধুমাত্র
    0.76
     Priya
    0.76
     Gaya
    0.74
     Buzz
    0.73
     Alessandro
    0.73
     Francesco
    0.72
     KON
    0.72
     вечер
    0.71
     Swami
    0.71
    Act Density 0.002%

    No Known Activations