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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrink
    -0.06
     처음
    -0.06
     чи
    -0.06
     ResourceBundle
    -0.06
    市
    -0.06
    .Destroy
    -0.06
     longitud
    -0.05
    _terminal
    -0.05
     fullWidth
    -0.05
     Dir
    -0.05
    POSITIVE LOGITS
    urers
    0.07
    ۰۰
    0.06
     ре
    0.06
    ﾄ
    0.06
    分布
    0.06
     potatoes
    0.06
     ओर
    0.06
    IK
    0.06
    偏
    0.06
    WS
    0.06
    Act Density 0.000%

    No Known Activations