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

    Neuronpedia

    INDEX
    Explanations

    say "[related to] families"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfermed
    -0.07
    宥
    -0.07
    something
    -0.07
    动荡
    -0.07
    效
    -0.07
    前列腺
    -0.06
    setState
    -0.06
    精神病
    -0.06
    分彩
    -0.06
    _tot
    -0.06
    POSITIVE LOGITS
    씸
    0.07
     Москвы
    0.07
    同學
    0.07
     Bern
    0.07
     NSMutableDictionary
    0.07
     Merc
    0.07
    /)
    0.07
    把手
    0.06
    西医
    0.06
    ud
    0.06
    Act Density 0.026%

    No Known Activations