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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ();
↵
↵
    -0.07
    لت
    -0.06
    ष
    -0.06
     ファ
    -0.06
     char
    -0.06
     hdf
    -0.06
    ozí
    -0.06
    (rb
    -0.06
     Tòa
    -0.06
    	P
    -0.06
    POSITIVE LOGITS
    FileType
    0.07
    Whitespace
    0.06
     exemple
    0.06
     viele
    0.06
     Cohen
    0.06
     northeastern
    0.06
    Misc
    0.06
     deepest
    0.06
     Diary
    0.06
     schö
    0.06
    Act Density 0.003%

    No Known Activations