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

    Neuronpedia

    INDEX
    Explanations

    expectations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pixels
    -0.08
    Observation
    -0.08
    /edit
    -0.08
    .o
    -0.08
     Observation
    -0.08
     observation
    -0.07
    orie
    -0.07
     OB
    -0.07
     الرب
    -0.07
     pixel
    -0.07
    POSITIVE LOGITS
     формат
    0.09
     stakeholders
    0.08
    _encoded
    0.08
     Новости
    0.08
    塑
    0.08
    	format
    0.08
     Пока
    0.08
    (expect
    0.08
    (format
    0.08
    ിനിമ
    0.08
    Act Density 0.004%

    No Known Activations