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

    Neuronpedia

    INDEX
    Explanations

    subscript indices like ₂

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     madrugada
    0.76
     polémica
    0.73
     porcentaje
    0.71
    roversial
    0.69
    後半
    0.68
     intestino
    0.68
     परसेंटेज
    0.67
     اكبر
    0.65
    ৪৮
    0.65
     batalha
    0.65
    POSITIVE LOGITS
    m
    0.77
     पाठ्यक्रमों
    0.60
    substack
    0.59
    j
    0.58
    ल
    0.57
     இந்த
    0.57
     Tento
    0.56
     Acta
    0.55
     ఇందు
    0.55
    g
    0.55
    Act Density 0.005%

    No Known Activations