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

    Neuronpedia

    INDEX
    Explanations

    mentions related to dates and locations in a narrative context

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

    Numbers followed by "per cent" or percentage

    np_acts-logits-general · gemini-2.0-flash

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.80
     Utilizing
    -0.80
    beled
    -0.76
    RegressionTest
    -0.75
     endeavored
    -0.75
    ViewImports
    -0.73
     intptr
    -0.73
     Utilize
    -0.71
    mybatisplus
    -0.71
     mold
    -0.71
    POSITIVE LOGITS
    guardian
    0.53
    theguardian
    0.52
     şi
    0.52
     defence
    0.50
     programme
    0.50
     Fifa
    0.49
     ţ
    0.47
     civilised
    0.46
     froide
    0.46
     Photograph
    0.46
    Act Density 0.075%

    No Known Activations