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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Từ
    -0.07
     Meng
    -0.07
     Alias
    -0.07
     Dimension
    -0.06
    納
    -0.06
    331
    -0.06
    _AD
    -0.06
     TPP
    -0.06
     berk
    -0.06
     Jin
    -0.06
    POSITIVE LOGITS
     corpses
    0.07
    美国
    0.06
    )d
    0.06
     عالية
    0.06
    !).
    0.06
    )))↵↵
    0.06
     screens
    0.06
    _ratings
    0.06
     hood
    0.06
    ↵↵↵
    0.06
    Act Density 0.003%

    No Known Activations