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

    Neuronpedia

    INDEX
    Explanations

    explanation of example usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exemples
    0.86
     exemplos
    0.86
     ejemplo
    0.86
     exemplu
    0.85
     ejemplos
    0.83
     przykład
    0.83
     примере
    0.82
     örnek
    0.79
    ແລະ
    0.72
     उदाहरण
    0.71
    POSITIVE LOGITS
    r
    0.95
    지만
    0.69
    ons
    0.62
    ী
    0.62
    تها
    0.61
    the
    0.61
    ONS
    0.61
    d
    0.61
    ire
    0.59
    ad
    0.59
    Act Density 0.076%

    No Known Activations