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

    Neuronpedia

    INDEX
    Explanations

    helpful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )])
    0.59
     दोस्तों
    0.55
     quantification
    0.53
     WL
    0.53
     полови
    0.52
     가지고
    0.50
     ))->
    0.49
    നോ
    0.48
     bhas
    0.48
     Тимо
    0.47
    POSITIVE LOGITS
    MAC
    0.48
    د
    0.47
    可
    0.47
    ologie
    0.46
     heut
    0.46
    SER
    0.46
    奖
    0.46
    pee
    0.45
    BANK
    0.45
    ర్స్
    0.45
    Act Density 0.001%

    No Known Activations