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

    Neuronpedia

    INDEX
    Explanations

    and to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ículo
    -0.06
    .ttf
    -0.06
    ;',↵
    -0.06
    ura
    -0.06
     yaptık
    -0.06
    _position
    -0.06
    .m
    -0.06
    র
    -0.06
     wears
    -0.06
    "
↵
    -0.06
    POSITIVE LOGITS
     Exiting
    0.07
    parency
    0.07
    character
    0.06
    Infinity
    0.06
    kara
    0.06
    립니다
    0.06
    [((
    0.06
    (sel
    0.06
     Vor
    0.06
    Fizz
    0.06
    Act Density 0.165%

    No Known Activations