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

    Neuronpedia

    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тис
    -0.07
    -be
    -0.07
    测
    -0.07
     worse
    -0.06
    -В
    -0.06
     tidal
    -0.06
     passages
    -0.06
    _bootstrap
    -0.06
    ployment
    -0.06
    iversal
    -0.06
    POSITIVE LOGITS
    Sha
    0.07
    	freopen
    0.07
     znaj
    0.06
     crea
    0.06
    dbuf
    0.06
    linik
    0.06
     uranus
    0.06
    /stats
    0.06
     게시
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations