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

    Neuronpedia

    INDEX
    Explanations

    noting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iens
    -0.07
    (Program
    -0.07
     guidelines
    -0.07
    Hardware
    -0.07
    Paul
    -0.07
    確
    -0.07
    迫不及待
    -0.06
     taco
    -0.06
     Groups
    -0.06
     rules
    -0.06
    POSITIVE LOGITS
     Voy
    0.08
    ายน
    0.07
    利用率
    0.07
    мот
    0.07
    こういう
    0.07
    сан
    0.07
    ﲰ
    0.06
    五月
    0.06
    🗨
    0.06
     ")↵↵
    0.06
    Act Density 0.007%

    No Known Activations