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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    문화
    -0.06
     여성
    -0.06
    ackers
    -0.06
    /R
    -0.06
    876
    -0.06
     Leer
    -0.06
    ţ
    -0.06
     Hats
    -0.06
     Jahres
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     crumbling
    0.07
    (post
    0.07
     MOV
    0.07
     самой
    0.07
    #__
    0.07
     Düş
    0.06
    	DECLARE
    0.06
    ,[
    0.06
    ainen
    0.06
     kterým
    0.06
    Act Density 0.056%

    No Known Activations