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

    Neuronpedia

    INDEX
    Explanations

    comparisons or choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flying
    -0.06
    372
    -0.06
    ileş
    -0.06
    compat
    -0.06
     Courage
    -0.06
     tiện
    -0.06
     його
    -0.06
     거
    -0.06
    -buffer
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    -pencil
    0.07
     wholesome
    0.06
    BER
    0.06
    .sendMessage
    0.06
    身份
    0.06
    nze
    0.06
    (dm
    0.06
    -parameter
    0.06
     miglior
    0.06
     vur
    0.06
    Act Density 0.050%

    No Known Activations