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

    Neuronpedia

    INDEX
    Explanations

    temperatures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explosives
    -0.08
    陬
    -0.08
     unfolding
    -0.08
     Author
    -0.07
    瓿
    -0.07
     inclination
    -0.07
    .*(
    -0.07
    较差
    -0.07
    瀏覽器
    -0.07
    Exactly
    -0.07
    POSITIVE LOGITS
    ель
    0.07
     West
    0.06
     instruments
    0.06
    希尔
    0.06
    omega
    0.06
     Frem
    0.06
    厘米
    0.06
    xy
    0.06
    .named
    0.06
    ようになった
    0.06
    Act Density 0.004%

    No Known Activations