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

    Neuronpedia

    INDEX
    Explanations

    formulas and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Нес
    -0.09
    .gallery
    -0.08
     выступ
    -0.08
    ahead
    -0.08
    .carousel
    -0.08
    carousel
    -0.08
     모습
    -0.08
    gallery
    -0.08
     orphan
    -0.08
     ಸಂಘ
    -0.08
    POSITIVE LOGITS
     formula
    0.13
    公式
    0.12
     Formula
    0.11
     fórmula
    0.11
    Formula
    0.11
     empirical
    0.10
     सूत्र
    0.10
     empir
    0.10
    formula
    0.10
    _formula
    0.10
    Act Density 0.020%

    No Known Activations