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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     университ
    -0.07
    妻
    -0.06
     dimensions
    -0.06
    ьми
    -0.06
    cw
    -0.06
     shark
    -0.06
    _tid
    -0.06
     smaller
    -0.06
     toilets
    -0.06
    descricao
    -0.06
    POSITIVE LOGITS
    نویس
    0.07
    	MessageBox
    0.07
     alertController
    0.07
    ثال
    0.07
     uplifting
    0.07
    ンプ
    0.07
    (dirname
    0.06
    ічна
    0.06
    [Any
    0.06
    ,*
    0.06
    Act Density 0.003%

    No Known Activations