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

    Neuronpedia

    INDEX
    Explanations

    unicode character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revolver
    -0.08
    His
    -0.07
    _exports
    -0.07
     min
    -0.07
    .Transfer
    -0.07
     whim
    -0.07
     Ber
    -0.07
    GetProperty
    -0.07
     Seç
    -0.07
    _projection
    -0.07
    POSITIVE LOGITS
     pošk
    0.07
     histogram
    0.06
    239
    0.06
     mutil
    0.06
    青
    0.06
    ubble
    0.06
    ，不
    0.06
     LGBTQ
    0.05
    (IOException
    0.05
    呆
    0.05
    Act Density 0.004%

    No Known Activations