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

    Neuronpedia

    INDEX
    Explanations

    flat screen television

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.50
    鐒
    0.50
    於是
    0.47
    ದುಕೊಳ್ಳ
    0.47
    を集
    0.46
    لي
    0.45
    ที่
    0.45
    ton
    0.45
    嘜
    0.45
     humide
    0.44
    POSITIVE LOGITS
    astre
    0.48
    okkal
    0.45
    ukaan
    0.45
    osed
    0.44
    aad
    0.44
     sported
    0.43
     качества
    0.43
    encoding
    0.43
     поля
    0.42
    نوات
    0.42
    Act Density 0.000%

    No Known Activations