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

    Neuronpedia

    INDEX
    Explanations

    core idea/principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Большая
    0.76
     Okinawa
    0.75
     тер
    0.75
     рода
    0.73
     ус
    0.73
     Ст
    0.72
    る
    0.72
     От
    0.71
     Ан
    0.71
    ян
    0.70
    POSITIVE LOGITS
    biome
    0.83
    ظمة
    0.71
    یرو
    0.70
    mix
    0.69
    bulan
    0.69
     interventi
    0.69
    wirkungen
    0.68
    apie
    0.67
    ەیە
    0.67
    wave
    0.67
    Act Density 0.001%

    No Known Activations