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

    Neuronpedia

    INDEX
    Explanations

    years in the 1900s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    óis
    0.69
    perature
    0.68
     یقینی
    0.67
    dzić
    0.66
    ogeneities
    0.66
    iczny
    0.65
     لاک
    0.64
    czeń
    0.64
    oxal
    0.63
    izacja
    0.63
    POSITIVE LOGITS
    ૯
    0.86
    0.77
    0.77
    9
    0.77
     Ninety
    0.76
    ಲೇ
    0.74
    ೯
    0.73
    ၉
    0.72
    Bert
    0.72
    ᱙
    0.71
    Act Density 0.102%

    No Known Activations