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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron spotlights fragments of the file‐header (the copyright/year/author signature block), e.g. bits of the year and the author’s name/email.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    IMPORTANT
    -0.07
     doesnt
    -0.07
    _bool
    -0.06
     coursework
    -0.06
    ･･
    -0.06
     toho
    -0.06
     Male
    -0.06
    those
    -0.06
     PLL
    -0.06
    ้าหน
    -0.06
    POSITIVE LOGITS
     artery
    0.07
    EXTERN
    0.07
     charset
    0.07
    -axis
    0.07
    _engine
    0.06
    -cache
    0.06
     Invasion
    0.06
    -a
    0.06
     outliers
    0.06
    %\
    0.06
    Act Density 0.007%

    No Known Activations