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

    Neuronpedia

    INDEX
    Explanations

    DEFAULT NULL, CURRENT_TIMESTAMP, NOW

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.30
    ’’
    1.26
    li
    1.20
    맑
    1.19
    ''''
    1.18
    ";}
    1.14
    ");
    1.13
    رض
    1.10
    會有
    1.09
    ")
    1.07
    POSITIVE LOGITS
    ovanja
    1.13
    zelfde
    1.13
    сная
    1.13
     Anche
    1.10
    нга
    1.10
     afar
    1.09
    шкан
    1.08
    asjoner
    1.07
    borhood
    1.05
    verwaltung
    1.05
    Act Density 0.001%

    No Known Activations