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

    Neuronpedia

    INDEX
    Explanations

    accesses or permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nejen
    0.62
     всех
    0.61
    Какие
    0.61
    सभी
    0.57
     wszystkich
    0.57
    Jangan
    0.57
     всі
    0.56
     Semua
    0.56
     semua
    0.53
    adhar
    0.53
    POSITIVE LOGITS
     peuvent
    0.73
     possono
    0.67
     mogą
    0.67
    也可
    0.66
     accesses
    0.63
     overseeing
    0.63
    也可以
    0.61
     può
    0.61
     môžu
    0.61
     pourrait
    0.61
    Act Density 0.000%

    No Known Activations