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

    Neuronpedia

    INDEX
    Explanations

    unintelligibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     да
    -0.08
    andex
    -0.07
     دقيقة
    -0.07
    .module
    -0.07
     مو
    -0.07
    rawler
    -0.07
    봬
    -0.07
     loader
    -0.07
    赛事
    -0.06
    旅客
    -0.06
    POSITIVE LOGITS
    .innerHTML
    0.07
    Disposition
    0.07
    Կ
    0.07
    �
    0.07
    Ascii
    0.07
    _CLEAN
    0.07
    _dispatch
    0.07
    économie
    0.07
    pics
    0.06
    热情
    0.06
    Act Density 0.087%

    No Known Activations