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

    Neuronpedia

    INDEX
    Explanations

    category theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hist
    -0.08
     Drop
    -0.08
    (bin
    -0.07
     Dans
    -0.07
     SEND
    -0.07
    抽查
    -0.07
     belly
    -0.06
    输送
    -0.06
     Press
    -0.06
    构件
    -0.06
    POSITIVE LOGITS
    urança
    0.08
    .relu
    0.07
    _WARN
    0.07
    Õ
    0.07
    скор
    0.07
     hạnh
    0.07
    URLException
    0.07
    icious
    0.07
     англий
    0.07
    റ
    0.07
    Act Density 0.007%

    No Known Activations