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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ddy
    -0.26
    rop
    -0.25
     Rut
    -0.24
     refused
    -0.24
    orp
    -0.24
    羣è¯ļ
    -0.24
    驳
    -0.24
    Reject
    -0.23
    aj
    -0.23
    .Apply
    -0.23
    POSITIVE LOGITS
    _lite
    0.28
    uxtap
    0.27
    æĤĦ
    0.27
     RETURNS
    0.25
    æ§ĺ
    0.24
     taller
    0.24
    imin
    0.24
    _exports
    0.24
    æģ°
    0.23
    åѦ龸
    0.23
    Act Density 0.132%

    No Known Activations