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

    Neuronpedia

    INDEX
    Explanations

    specifications related to technical performance and efficiency metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    distance and angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.44
    classnames
    -0.33
    tgz
    -0.32
     bosh
    -0.29
    бята
    -0.28
     hand
    -0.28
     trasc
    -0.28
     säker
    -0.27
    ']):
    -0.27
    multer
    -0.27
    POSITIVE LOGITS
     ModelExpression
    0.73
    HasAnnotation
    0.58
    MessageTagHelper
    0.57
     surla
    0.56
     '\\;'
    0.54
    TagMode
    0.52
    optional
    0.51
    memoized
    0.50
    JspWriter
    0.50
     насељу
    0.50
    Act Density 0.058%

    No Known Activations