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

    Neuronpedia

    INDEX
    Explanations

    multiple languages / internet abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лада
    -0.06
    abytes
    -0.06
     Herald
    -0.06
     avanz
    -0.06
     skew
    -0.06
    ilent
    -0.06
    값
    -0.06
    .Depth
    -0.06
     railways
    -0.06
     belg
    -0.06
    POSITIVE LOGITS
     thích
    0.09
     Birleşik
    0.06
    	dto
    0.06
     waved
    0.06
    lacağ
    0.06
    |--------------------------------------------------------------------------↵
    0.06
    Liked
    0.06
     Continental
    0.06
     탈
    0.06
     charming
    0.06
    Act Density 0.045%

    No Known Activations