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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    джер
    -0.07
    romosome
    -0.07
     الإن
    -0.07
    疖
    -0.07
    _dic
    -0.07
    shi
    -0.07
    itrust
    -0.07
    "If
    -0.07
     Fischer
    -0.07
    _guide
    -0.06
    POSITIVE LOGITS
    np
    0.08
    록
    0.07
    概率
    0.07
    ерт
    0.07
    シャル
    0.07
     gab
    0.07
    薜
    0.07
    mons
    0.06
    prop
    0.06
    engkap
    0.06
    Act Density 0.011%

    No Known Activations