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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    スト
    -0.07
    스트
    -0.07
     Soap
    -0.07
     award
    -0.06
    iors
    -0.06
    _gap
    -0.06
    _DT
    -0.06
    니스
    -0.06
     Phil
    -0.06
    _subject
    -0.06
    POSITIVE LOGITS
    다는
    0.07
    orum
    0.06
    /************************************************************************************************
    0.06
    wm
    0.06
    隐
    0.06
     WHATSOEVER
    0.06
     trump
    0.06
     sass
    0.06
     explicitly
    0.06
    {EIF
    0.05
    Act Density 0.027%

    No Known Activations