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

    Neuronpedia

    INDEX
    Explanations

    Baywatch lifeguard questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蛋糕
    0.46
    س
    0.46
    有效
    0.45
    integrity
    0.44
    imis
    0.43
    ۵
    0.43
    lah
    0.43
    ل
    0.43
    ız
    0.43
    }$')
    0.42
    POSITIVE LOGITS
    内に
    0.48
    を一
    0.48
     destacar
    0.45
     muscul
    0.44
     ent
    0.44
     оказался
    0.43
     Hadley
    0.43
     viste
    0.43
     pick
    0.43
    䧉
    0.43
    Act Density 0.000%

    No Known Activations