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

    Neuronpedia

    INDEX
    Explanations

    probabilities and standard deviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ғыс
    -0.08
    klad
    -0.08
    (Sub
    -0.08
    _vectors
    -0.08
    441
    -0.08
    (contact
    -0.08
    845
    -0.07
    ciaux
    -0.07
    chauff
    -0.07
     капит
    -0.07
    POSITIVE LOGITS
    :CGRect
    0.09
    -between
    0.08
    FROM
    0.08
     consecutive
    0.08
     Zeitraum
    0.08
    WINDOW
    0.08
    -window
    0.08
     промеж
    0.08
    Window
    0.07
     Ambos
    0.07
    Act Density 0.017%

    No Known Activations