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

    Neuronpedia

    INDEX
    Explanations

    class/widget names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不由
    0.87
     voidaan
    0.81
     Moż
    0.80
     gacchati
    0.80
    处理器
    0.79
     Qxb
    0.79
     appellee
    0.79
    を務
    0.78
     culprits
    0.77
    它可以
    0.75
    POSITIVE LOGITS
     सामाजिक
    0.71
    ках
    0.70
    content
    0.66
    centre
    0.65
     content
    0.64
    Roh
    0.64
    OH
    0.63
    cia
    0.63
    setContent
    0.63
    Укра
    0.62
    Act Density 0.001%

    No Known Activations