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

    Neuronpedia

    INDEX
    Explanations

    Build logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蓁
    -0.08
    elage
    -0.07
    istinguished
    -0.07
     dtype
    -0.07
    (WIN
    -0.06
    ╜
    -0.06
     graves
    -0.06
    /locale
    -0.06
    toThrow
    -0.06
    elize
    -0.06
    POSITIVE LOGITS
    環境
    0.07
     SHORT
    0.07
     사회
    0.07
    Scrollbar
    0.07
     Phật
    0.07
    阻
    0.07
     ####
    0.07
     Technology
    0.07
    aker
    0.07
    ビー
    0.06
    Act Density 0.008%

    No Known Activations