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

    Neuronpedia

    INDEX
    Explanations

    A followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     véritable
    0.80
     بہانہ
    0.77
     بچہ
    0.76
     انتہائی
    0.76
     multifaceted
    0.73
     supremely
    0.73
     उनकी
    0.73
     Così
    0.73
    emptyDict
    0.73
     Şimdi
    0.72
    POSITIVE LOGITS
     or
    1.08
    ம்
    0.81
     rows
    0.79
     digits
    0.79
     dimers
    0.79
     coasters
    0.79
    ies
    0.78
     neutrinos
    0.78
     phonons
    0.75
     and
    0.74
    Act Density 0.076%

    No Known Activations