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

    Neuronpedia

    INDEX
    Explanations

    contractions with ’

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilisez
    0.38
     utilizzando
    0.38
     utilisent
    0.37
     utilizando
    0.35
     Regex
    0.34
     используются
    0.34
     usando
    0.33
     باستخدام
    0.33
     numeri
    0.33
    }\
    0.33
    POSITIVE LOGITS
    Justice
    0.33
     emo
    0.31
    ска
    0.31
     Coronation
    0.30
    Assassin
    0.29
    HOR
    0.29
     brisket
    0.29
    IGAN
    0.29
    గా
    0.29
     בא
    0.29
    Act Density 0.000%

    No Known Activations