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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quel
    -0.07
    ordova
    -0.07
    笯
    -0.06
     Aly
    -0.06
    :num
    -0.06
     titleLabel
    -0.06
    ----↵↵
    -0.06
    🆒
    -0.06
    楙
    -0.06
    Compose
    -0.06
    POSITIVE LOGITS
    riminal
    0.07
    facility
    0.07
    %',↵
    0.07
    تصرف
    0.06
    iens
    0.06
    מבוגרים
    0.06
     Feel
    0.06
     enfrent
    0.06
    LAT
    0.06
    REV
    0.06
    Act Density 0.015%

    No Known Activations