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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Classified
    -0.07
     stale
    -0.07
     ale
    -0.07
    ateg
    -0.07
    bench
    -0.06
    Wrapped
    -0.06
    480
    -0.06
    Concurrency
    -0.06
     noses
    -0.06
    contro
    -0.06
    POSITIVE LOGITS
     gcd
    0.07
    .;↵
    0.07
    訪
    0.06
    RS
    0.06
     '&#
    0.06
     <$
    0.06
     مرب
    0.06
     الوف
    0.06
     Loader
    0.06
     worldly
    0.06
    Act Density 0.031%

    No Known Activations