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

    Neuronpedia

    INDEX
    Explanations

    basic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .translate
    -0.07
     throughput
    -0.07
    wipe
    -0.07
     директор
    -0.06
    .Fl
    -0.06
     tours
    -0.06
     pais
    -0.06
     ListViewItem
    -0.06
     UIColor
    -0.06
    ivatel
    -0.06
    POSITIVE LOGITS
     конс
    0.07
     relies
    0.07
    ตร
    0.07
     표현
    0.06
     rẻ
    0.06
    	headers
    0.06
    memberof
    0.06
     дело
    0.06
     capac
    0.06
     Sham
    0.06
    Act Density 0.030%

    No Known Activations