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

    Neuronpedia

    INDEX
    Explanations

    just + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    걍
    2.67
    و
    2.42
    ным
    2.20
    ко
    2.17
    ست
    2.14
    ется
    2.11
    ром
    2.09
    ного
    2.06
    ка
    2.03
     elucid
    1.95
    POSITIVE LOGITS
    ifiably
    3.88
    ート
    2.03
     таки
    1.96
    inth
    1.91
    larni
    1.88
    ール
    1.84
    meter
    1.83
    inė
    1.83
    michael
    1.83
    lly
    1.82
    Act Density 0.454%

    No Known Activations