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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edes
    -0.06
    retty
    -0.06
    났
    -0.06
    *math
    -0.06
    idla
    -0.06
    verbatim
    -0.06
    CAR
    -0.06
    mekte
    -0.05
    ーラ
    -0.05
     doctoral
    -0.05
    POSITIVE LOGITS
    	cpu
    0.07
     özgür
    0.07
     Af
    0.07
    agnetic
    0.07
    Months
    0.07
     کنترل
    0.07
    Sau
    0.07
     поль
    0.06
     پس
    0.06
    .—
    0.06
    Act Density 0.001%

    No Known Activations