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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datatype
    -0.08
    trs
    -0.08
     SJ
    -0.07
    닫
    -0.07
    strt
    -0.07
    gnu
    -0.07
     cst
    -0.07
    嗜
    -0.07
     timeZone
    -0.07
    gó
    -0.07
    POSITIVE LOGITS
    ']='
    0.07
    mayacağı
    0.06
    📒
    0.06
    ﹱ
    0.06
    舥
    0.06
    أحك
    0.06
    ộc
    0.06
    裔
    0.06
    ADOW
    0.06
    国人
    0.06
    Act Density 0.000%

    No Known Activations