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

    Neuronpedia

    INDEX
    Explanations

    spell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     варт
    -0.07
     Literature
    -0.07
    ctp
    -0.06
     závě
    -0.06
    administration
    -0.06
    asics
    -0.06
    ilihan
    -0.06
    _irq
    -0.06
     segmentation
    -0.06
     khoán
    -0.06
    POSITIVE LOGITS
     ديسمبر
    0.06
    ью
    0.06
    moves
    0.06
    né
    0.06
     strengthens
    0.06
    İng
    0.06
    (className
    0.06
    ์อ
    0.06
    �
    0.06
    ние
    0.06
    Act Density 0.014%

    No Known Activations