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

    Neuronpedia

    INDEX
    Explanations

    pussy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.88
    :
    0.80
    ः
    0.71
    ers
    0.71
     в
    0.66
    ।’’
    0.66
     a
    0.66
    alir
    0.66
    anie
    0.64
     ग्ले
    0.63
    POSITIVE LOGITS
    m
    0.68
    κ
    0.66
    ای
    0.57
    |)
    0.56
    GLOBALS
    0.56
    の新
    0.56
    نگ
    0.55
    “
    0.54
    шо
    0.53
    ቻ
    0.53
    Act Density 0.001%

    No Known Activations