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

    Neuronpedia

    INDEX
    Explanations

    Khan Academy learning resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DD
    0.72
     servizio
    0.71
     woning
    0.68
    त्तीस
    0.66
    DOCT
    0.66
     miał
    0.63
    NG
    0.63
    FEN
    0.63
     settembre
    0.63
     mwaka
    0.61
    POSITIVE LOGITS
    us
    0.74
    h
    0.74
    rl
    0.73
    ص
    0.73
    k
    0.72
    all
    0.70
    n
    0.70
    v
    0.69
    ри
    0.68
    td
    0.68
    Act Density 0.004%

    No Known Activations