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

    Neuronpedia

    INDEX
    Explanations

    impact of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ור
    1.13
    ныгы
    1.05
    Վ
    0.95
    Το
    0.93
    ডো
    0.93
    коль
    0.93
    blooded
    0.90
    бро
    0.89
    ב
    0.89
    жээ
    0.88
    POSITIVE LOGITS
     Auswirkungen
    1.52
     impacto
    1.43
    影响
    1.41
     effects
    1.38
     Effects
    1.32
     efeitos
    1.32
     impactos
    1.31
    effects
    1.29
     consequences
    1.28
    Effects
    1.27
    Act Density 0.003%

    No Known Activations