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

    Neuronpedia

    INDEX
    Explanations

    tailor suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵↵
    0.91
     You
    0.91
     Đây
    0.89
     Emotions
    0.88
     Please
    0.87
     Something
    0.87
     emozioni
    0.83
     Boxer
    0.83
    ↵↵
    0.83
     Everyone
    0.83
    POSITIVE LOGITS
    ſt
    0.73
     damal
    0.65
     parasit
    0.64
    $-[
    0.63
    バリ
    0.63
    ̄
    0.63
    }{*}{}
    0.63
    )|\
    0.63
    fl
    0.63
    ళ్ల
    0.62
    Act Density 0.187%

    No Known Activations