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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adir
    -0.07
    론
    -0.06
    cret
    -0.06
    orado
    -0.06
     menn
    -0.06
    tt
    -0.06
     끝
    -0.06
     silver
    -0.06
    dice
    -0.06
     Wendy
    -0.06
    POSITIVE LOGITS
    ?-
    0.07
    ;',↵
    0.07
     qs
    0.07
    宗
    0.06
    ／／
    0.06
     toto
    0.06
     UCLA
    0.06
     çıkış
    0.06
                              ↵
    0.06
     texas
    0.06
    Act Density 0.006%

    No Known Activations