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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人的
    -0.08
     Sticky
    -0.06
     rigorous
    -0.06
    襁
    -0.06
    每个人的
    -0.06
     immunity
    -0.06
    Precio
    -0.06
    功率
    -0.06
    挑衅
    -0.06
    終於
    -0.06
    POSITIVE LOGITS
    adc
    0.08
    ancellation
    0.07
    fe
    0.07
    abbr
    0.07
    𝚑
    0.07
    关
    0.07
     farmers
    0.06
    �
    0.06
    оп
    0.06
    氖
    0.06
    Act Density 0.006%

    No Known Activations