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

    Neuronpedia

    INDEX
    Explanations

    final amount, mass, energy, sum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eintrag
    0.68
     Temperatur
    0.67
    phalodes
    0.66
    verage
    0.66
     sorgt
    0.65
     suffisamment
    0.65
     Якщо
    0.62
    淉
    0.62
    Temper
    0.61
    ˏ
    0.61
    POSITIVE LOGITS
    最终
    0.70
    新的
    0.66
     pursuance
    0.65
    ivé
    0.65
    焕
    0.65
     funds
    0.64
    يع
    0.64
    返回
    0.64
    当天
    0.64
    }^{+},
    0.63
    Act Density 0.002%

    No Known Activations