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

    Neuronpedia

    INDEX
    Explanations

    software distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     efectos
    0.53
     perfekt
    0.42
     effets
    0.41
    の効果
    0.41
     Kih
    0.40
     코드
    0.40
    的效果
    0.39
     realises
    0.39
     perfek
    0.39
     arquivo
    0.38
    POSITIVE LOGITS
     Distribution
    0.51
    Distribution
    0.48
     distribution
    0.46
     توزيع
    0.42
    FullScreen
    0.42
    upati
    0.41
     ethic
    0.39
    وزيع
    0.39
    isterschaft
    0.39
     Subscription
    0.38
    Act Density 0.001%

    No Known Activations