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

    Neuronpedia

    INDEX
    Explanations

    Domestic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अनिवार्य
    0.75
    ceti
    0.72
     Serious
    0.71
     పి
    0.71
    <unused1874>
    0.69
     PIN
    0.68
    hoch
    0.68
     Florida
    0.68
    വിധ
    0.68
    Serious
    0.67
    POSITIVE LOGITS
     violence
    1.07
    Violence
    0.92
    violence
    0.92
     violent
    0.91
     violencia
    0.88
     beat
    0.88
     Violence
    0.85
    暴力
    0.82
     violently
    0.81
    violent
    0.80
    Act Density 0.007%

    No Known Activations