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

    Neuronpedia

    INDEX
    Explanations

    variations of the same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ২০১৭
    0.45
    と感じ
    0.43
    ರದ
    0.42
     заклад
    0.40
     +(
    0.39
     这
    0.39
    的原因
    0.38
     Freitag
    0.38
    䂧
    0.38
     इंतजाम
    0.38
    POSITIVE LOGITS
    SH
    0.57
    Charge
    0.57
    ing
    0.56
    SM
    0.54
     are
    0.53
    SCALE
    0.53
    TI
    0.52
    bottle
    0.50
    ING
    0.50
    components
    0.49
    Act Density 0.003%

    No Known Activations