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

    Neuronpedia

    INDEX
    Explanations

    network detection and infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сей
    1.81
    тся
    1.74
    け
    1.68
    шему
    1.66
    ון
    1.61
    šana
    1.60
     наличие
    1.57
     ответствен
    1.56
    δήποτε
    1.55
    ão
    1.48
    POSITIVE LOGITS
    ל
    2.17
     plabic
    1.93
    shops
    1.76
    i
    1.73
     whence
    1.73
     macarons
    1.72
    ST
    1.68
    م
    1.68
     accordingly
    1.67
     milled
    1.67
    Act Density 0.043%

    No Known Activations