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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /comment
    -0.06
    footer
    -0.06
    ıyı
    -0.06
     maxSize
    -0.06
     Explosion
    -0.06
    Typography
    -0.06
     explosion
    -0.06
     들어
    -0.06
     ند
    -0.06
     aup
    -0.06
    POSITIVE LOGITS
    ead
    0.07
    ICLES
    0.07
     Hon
    0.07
    OPTION
    0.07
     реш
    0.06
    spar
    0.06
    Finding
    0.06
    ницы
    0.06
    蜘蛛
    0.06
    λαν
    0.06
    Act Density 0.221%

    No Known Activations