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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fitzgerald
    -0.08
    ؾ
    -0.08
     ?>'
    -0.07
    私の
    -0.07
     Hindus
    -0.07
     resting
    -0.07
     timespec
    -0.07
     Sikh
    -0.07
    .stats
    -0.07
     Neville
    -0.07
    POSITIVE LOGITS
    센
    0.08
     licenses
    0.08
    另外
    0.07
    larınızı
    0.07
    名义
    0.07
    📰
    0.06
     *</
    0.06
    服务商
    0.06
    直通车
    0.06
    慵
    0.06
    Act Density 0.049%

    No Known Activations