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
     onFailure
    -0.07
     audience
    -0.07
    	sum
    -0.07
     Piece
    -0.07
    "]));↵
    -0.06
    .Grid
    -0.06
    "));
↵
↵
    -0.06
     quality
    -0.06
    .SIG
    -0.06
    POSITIVE LOGITS
     кня
    0.07
    领导
    0.07
     Braves
    0.06
    ーー
    0.06
     حاج
    0.06
     Centro
    0.06
     correspondence
    0.06
     kred
    0.06
    laması
    0.06
     documento
    0.06
    Act Density 0.000%

    No Known Activations