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

    Neuronpedia

    INDEX
    Explanations

    parser

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INS
    -0.07
    -by
    -0.07
     اصفهان
    -0.07
    OwnerId
    -0.07
     Ста
    -0.07
    mysqli
    -0.07
    DDL
    -0.07
     Foreign
    -0.06
    UTE
    -0.06
    (skip
    -0.06
    POSITIVE LOGITS
     systemic
    0.06
     diğer
    0.06
    珍
    0.06
    ritz
    0.06
        ↵
    0.06
     Flooring
    0.06
    tle
    0.06
     Girls
    0.06
    massage
    0.06
    _sdk
    0.06
    Act Density 0.014%

    No Known Activations