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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поступ
    -0.07
    nam
    -0.06
     Pump
    -0.06
     niệm
    -0.06
    AUTO
    -0.06
     Pou
    -0.06
     misery
    -0.06
    _destroy
    -0.06
     Erotic
    -0.06
    Holy
    -0.06
    POSITIVE LOGITS
    解决
    0.07
    如下
    0.07
    684
    0.07
    Collapsed
    0.07
    aging
    0.06
    駅徒歩
    0.06
    (frame
    0.06
     audit
    0.06
    Scaled
    0.06
     {↵↵
    0.06
    Act Density 0.000%

    No Known Activations