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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associations in data representations

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

    File names / URLs with numbers

    np_acts-logits-general · gemini-2.0-flash

    latex citations and code markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.62
    isRequired
    -0.45
    UnsafeEnabled
    -0.43
    GEBURTSDATUM
    -0.43
     sdf
    -0.43
    HideFlags
    -0.41
     hours
    -0.41
    ixels
    -0.40
     ouver
    -0.39
     dingin
    -0.38
    POSITIVE LOGITS
     ddelweddau
    0.73
    FunctionFlags
    0.72
    Kaynakça
    0.70
    下载附件
    0.70
    mybatisplus
    0.69
     disambiguazione
    0.66
    glise
    0.65
     bezeichneter
    0.64
    !*\
    0.64
    rouvez
    0.62
    Act Density 0.522%

    No Known Activations