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

    Neuronpedia

    INDEX
    Explanations

    Q: or black breath or we propose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MAXN
    -1.93
     you
    -1.89
     parachoque
    -1.76
    .
    -1.73
    RAD
    -1.72
    ANIUM
    -1.71
    雠
    -1.70
    XII
    -1.66
    ichtete
    -1.65
    -1.63
    POSITIVE LOGITS
     användas
    1.80
    quelize
    1.77
    سجيلات
    1.63
    Subgoals
    1.59
    řit
    1.56
    ramientas
    1.52
     mengangg
    1.52
     älskar
    1.50
     体験
    1.48
    ítmény
    1.48
    Act Density 0.000%

    No Known Activations