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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TRA
    -0.07
    vements
    -0.07
     частности
    -0.07
    .querySelectorAll
    -0.07
    党委
    -0.07
     Nearby
    -0.07
    JUnit
    -0.07
    거든요
    -0.06
    AtA
    -0.06
    .lucene
    -0.06
    POSITIVE LOGITS
    �
    0.08
    ж
    0.07
    _conf
    0.07
    ﾱ
    0.07
    ifter
    0.07
    rine
    0.06
    fre
    0.06
    식
    0.06
    �
    0.06
    ㈭
    0.06
    Act Density 0.011%

    No Known Activations