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

    Neuronpedia

    INDEX
    Explanations

    public static void main(String[] args)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يك
    0.61
    Ну
    0.57
    rable
    0.51
    Ги
    0.51
    ς
    0.50
    다고
    0.50
    رى
    0.50
    也
    0.49
    ів
    0.49
    وس
    0.49
    POSITIVE LOGITS
    to
    0.59
     بطور
    0.58
    tor
    0.56
    tooltip
    0.53
     जवळ
    0.52
     factorial
    0.51
    teaser
    0.50
    cas
    0.50
    number
    0.49
    ."),
    0.49
    Act Density 0.015%

    No Known Activations