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

    Neuronpedia

    INDEX
    Explanations

    distribution and engagement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    κ
    2.11
    ט
    1.80
    ки
    1.60
    ก
    1.59
    idane
    1.57
    л
    1.53
    ка
    1.53
    те
    1.53
    ва
    1.52
    ب
    1.49
    POSITIVE LOGITS
    thed
    1.66
    spf
    1.58
    𝐠
    1.58
    ように
    1.49
    Telegram
    1.41
    rei
    1.40
     возможно
    1.38
    tag
    1.35
     MeV
    1.34
     toneladas
    1.34
    Act Density 0.000%

    No Known Activations