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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -breaking
    -0.09
     bytes
    -0.08
    宴
    -0.08
    ändler
    -0.08
     breaches
    -0.08
    allocator
    -0.08
    idente
    -0.08
     экспер
    -0.07
     bestowed
    -0.07
    .CLIENT
    -0.07
    POSITIVE LOGITS
    公交
    0.13
    交通
    0.10
    徒歩
    0.10
    设施
    0.09
     miej
    0.09
     ônibus
    0.09
     subway
    0.09
     транспорта
    0.09
     passenger
    0.09
     ಸಾರ್ವಜನಿಕ
    0.09
    Act Density 0.042%

    No Known Activations