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

    Neuronpedia

    INDEX
    Explanations

    java javax imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्ट
    3.24
    もら
    3.23
     superconduct
    3.05
    tır
    3.01
    ्ट
    2.99
    años
    2.96
    ଼
    2.91
     sebesar
    2.90
    2.89
     рынка
    2.87
    POSITIVE LOGITS
    ′
    3.16
    withstanding
    2.87
    ান
    2.83
    v
    2.75
    viel
    2.64
    ″
    2.63
    ︎
    2.59
    ্স
    2.58
    __,
    2.55
    ively
    2.53
    Act Density 0.001%

    No Known Activations