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

    Neuronpedia

    INDEX
    Explanations

    disgust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shift
    -0.08
     add
    -0.08
     Dre
    -0.07
    加上
    -0.07
    .layer
    -0.07
     subset
    -0.07
     columnIndex
    -0.07
    encent
    -0.07
    .currentPage
    -0.07
     연결
    -0.07
    POSITIVE LOGITS
     gì
    0.07
    טבח
    0.07
    decoder
    0.06
    *sp
    0.06
    $arr
    0.06
    abi
    0.06
    깉
    0.06
    \Validator
    0.06
    .Blocks
    0.06
     suicide
    0.06
    Act Density 0.003%

    No Known Activations