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

    Neuronpedia

    INDEX
    Explanations

    auto racing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mechanisms
    -0.07
     canc
    -0.07
    _TEX
    -0.07
    总额
    -0.07
    createUrl
    -0.06
    סקר
    -0.06
    ՝
    -0.06
    dots
    -0.06
    .Q
    -0.06
     barric
    -0.06
    POSITIVE LOGITS
     Dimit
    0.08
    乔丹
    0.07
    ;br
    0.07
     binary
    0.07
    .UltraWin
    0.07
     Hyper
    0.07
     cairo
    0.07
    _));↵
    0.07
    حدث
    0.07
     pon
    0.07
    Act Density 0.011%

    No Known Activations