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

    Neuronpedia

    INDEX
    Explanations

    holy bible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    、
    0.73
    ،
    0.68
    פון
    0.61
    ری
    0.61
    Algun
    0.59
     ی
    0.59
    El
    0.58
    :
    0.58
    Seite
    0.57
    Caracter
    0.57
    POSITIVE LOGITS
     करण्याचा
    0.57
     surprising
    0.55
     Purposes
    0.55
     Traction
    0.55
     Correction
    0.54
     Bà
    0.54
     Bavaria
    0.54
    ften
    0.53
    檢查
    0.52
     Attractions
    0.52
    Act Density 0.000%

    No Known Activations