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

    Neuronpedia

    INDEX
    Explanations

    service descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺕ
    1.83
    bersome
    1.42
    ﺭ
    1.41
    蚪
    1.38
    ्य
    1.34
     \%$
    1.29
     ficando
    1.29
     existente
    1.28
    ésére
    1.28
    isées
    1.27
    POSITIVE LOGITS
    it
    1.98
    ס
    1.77
    1
    1.53
    2
    1.52
    9
    1.48
    с
    1.47
     ಸಲ್ಲ
    1.43
    and
    1.42
    5
    1.42
    7
    1.38
    Act Density 0.042%

    No Known Activations