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

    Neuronpedia

    INDEX
    Explanations

    Year, Mexico, Third Law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.98
    чні
    0.91
     ቦታ
    0.91
    żli
    0.91
    0.84
    calendar
    0.84
    \}}
    0.84
     seguenti
    0.84
    رائی
    0.82
    ポーツ
    0.82
    POSITIVE LOGITS
    ?
    0.86
     currently
    0.78
    !
    0.77
    ()
    0.73
     presently
    0.71
    ,
    0.68
     bereits
    0.67
    рель
    0.67
    ты
    0.67
    -
    0.66
    Act Density 0.000%

    No Known Activations