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

    Neuronpedia

    INDEX
    Explanations

    typicality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    positive
    -0.07
     negative
    -0.06
     goose
    -0.06
    -bearing
    -0.06
     باز
    -0.06
    -wh
    -0.06
     hectares
    -0.06
     NN
    -0.06
     positive
    -0.06
    -links
    -0.06
    POSITIVE LOGITS
     일반
    0.07
    istribution
    0.07
    áct
    0.07
     vz
    0.07
     обычно
    0.07
     обы
    0.07
     used
    0.06
     usual
    0.06
     Usually
    0.06
    annabin
    0.06
    Act Density 0.055%

    No Known Activations