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

    Neuronpedia

    INDEX
    Explanations

    numbers or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Threshold
    0.85
    ン
    0.80
     Ajouter
    0.80
    祥
    0.79
     خوبی
    0.78
    thing
    0.77
     الأصل
    0.77
     Compile
    0.77
    न
    0.77
     Viewed
    0.75
    POSITIVE LOGITS
    मिका
    0.80
    he
    0.75
    بعد
    0.72
    ende
    0.71
    פר
    0.71
    Após
    0.70
    បទ
    0.70
    嗖
    0.70
    มี
    0.69
    অন্যদিকে
    0.68
    Act Density 0.004%

    No Known Activations