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

    Neuronpedia

    INDEX
    Explanations

    ut

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Word
    -0.07
     пок
    -0.06
     incredibly
    -0.06
     additives
    -0.06
    	cpu
    -0.06
     cnn
    -0.06
    間に
    -0.06
    schemas
    -0.06
     ».
    -0.06
    -0.06
    POSITIVE LOGITS
    ΥΡ
    0.07
     runaway
    0.07
    rophy
    0.07
    оки
    0.07
    اتی
    0.07
    refresh
    0.07
    ี
    0.07
    erase
    0.06
     stě
    0.06
    urt
    0.06
    Act Density 0.002%

    No Known Activations