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

    Neuronpedia

    INDEX
    Explanations

    words associated with conversations, rules, and authority

    oai_token-act-pair · gemini-2.0-flash

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.81
    '
    -0.72
    ↵↵
    -0.69
     "
    -0.69
     in
    -0.68
     $
    -0.66
    ↵
    -0.66
     The
    -0.61
     for
    -0.60
     on
    -0.60
    POSITIVE LOGITS
     kasarigan
    1.38
    parsedMessage
    1.30
    tagHelperRunner
    1.21
     doubtnut
    1.19
     NSCoder
    1.16
    rungsseite
    1.15
    Tembelea
    1.12
     Himo
    1.09
     дописавши
    1.08
     betweenstory
    1.08
    Act Density 5.596%

    No Known Activations