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

    Neuronpedia

    INDEX
    Explanations

    Fractions and division

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mine
    -0.06
     gladly
    -0.06
    optional
    -0.06
     lic
    -0.06
     클래스
    -0.06
     lign
    -0.06
     RTL
    -0.06
    Enc
    -0.06
     Often
    -0.06
    ST
    -0.06
    POSITIVE LOGITS
    (bbox
    0.07
    _BIG
    0.06
     Bomb
    0.06
     Sellers
    0.06
    (chat
    0.06
    getTable
    0.06
     saat
    0.06
    ially
    0.06
    =test
    0.06
    withErrors
    0.06
    Act Density 0.019%

    No Known Activations