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

    Neuronpedia

    INDEX
    Explanations

    [](

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Authorize
    -0.07
    .djang
    -0.06
    ҏ
    -0.06
    ക
    -0.06
    _FC
    -0.06
    .JpaRepository
    -0.06
    风控
    -0.06
    篑
    -0.06
    .RESET
    -0.06
    .FLAG
    -0.06
    POSITIVE LOGITS
     eBay
    0.07
    赞扬
    0.07
     knife
    0.07
    _spacing
    0.07
    directory
    0.07
     MAD
    0.07
    Civil
    0.07
    _eff
    0.06
    jon
    0.06
     millennia
    0.06
    Act Density 0.001%

    No Known Activations