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

    Neuronpedia

    INDEX
    Explanations

    background color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Error
    0.63
     Cron
    0.61
    ээр
    0.58
     Leads
    0.58
     Slice
    0.57
     வந்தார்
    0.55
     Circular
    0.55
     Aleg
    0.54
     traverse
    0.54
     فإن
    0.54
    POSITIVE LOGITS
    rainbow
    0.72
    embed
    0.71
    bilder
    0.67
    coupon
    0.67
    luğ
    0.67
    ies
    0.67
    consulta
    0.67
    lunch
    0.66
    naph
    0.66
    ionization
    0.66
    Act Density 0.004%

    No Known Activations