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

    Neuronpedia

    INDEX
    Explanations

    liver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sled
    -0.08
    Sk
    -0.08
    Taking
    -0.07
    st
    -0.07
    ST
    -0.07
     Notice
    -0.07
    _execute
    -0.07
    _str
    -0.07
    SER
    -0.07
    提速
    -0.07
    POSITIVE LOGITS
     добав
    0.07
    ಐ
    0.07
    ꓽ
    0.07
     rơi
    0.06
    ⇣
    0.06
    ϐ
    0.06
    ($.
    0.06
    ⇙
    0.06
    珰
    0.06
    ⚏
    0.06
    Act Density 0.059%

    No Known Activations