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

    Neuronpedia

    INDEX
    Explanations

    On

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     potential
    -0.06
    Which
    -0.06
    predicate
    -0.06
    Quiz
    -0.06
     yaygın
    -0.06
    推荐
    -0.06
     insights
    -0.06
    strategy
    -0.06
    232
    -0.06
     Gul
    -0.06
    POSITIVE LOGITS
    .Metro
    0.07
    ños
    0.07
    unter
    0.07
     on
    0.07
    (`<
    0.07
     nbr
    0.07
    _FAMILY
    0.07
    ...");↵
    0.06
    On
    0.06
    :],
    0.06
    Act Density 0.022%

    No Known Activations