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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ile"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ched
    -0.07
    주의
    -0.07
    "]."
    -0.06
    ----------------------------------------------------------------------------
    -0.06
    版
    -0.06
    nelly
    -0.06
    588
    -0.06
     dam
    -0.06
    Fab
    -0.06
    الیا
    -0.06
    POSITIVE LOGITS
     Illustrator
    0.07
    .Style
    0.07
    enght
    0.07
     Typeface
    0.06
    Hibernate
    0.06
    .comments
    0.06
     Scalars
    0.06
     Singer
    0.06
     spur
    0.06
     лікар
    0.06
    Act Density 0.002%

    No Known Activations