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

    Neuronpedia

    INDEX
    Explanations

    Lack of surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lên
    -0.07
     decltype
    -0.07
     Після
    -0.07
     Synd
    -0.07
    ��드
    -0.07
     العالم
    -0.06
    .cg
    -0.06
    Court
    -0.06
     sürdür
    -0.06
     هواپیم
    -0.06
    POSITIVE LOGITS
     Bronx
    0.06
    SENSOR
    0.06
    Season
    0.06
    _DIG
    0.06
     fanatic
    0.06
    845
    0.06
     disple
    0.06
     horrifying
    0.06
    asket
    0.06
     tossed
    0.06
    Act Density 0.018%

    No Known Activations