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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical data and numerical comparisons

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

    only a few could

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nor
    -0.41
     !==
    -0.33
    吝
    -0.31
    !==
    -0.30
     Tourismus
    -0.30
    jarkan
    -0.30
     nowhere
    -0.29
    驾
    -0.29
     travers
    -0.29
     franchise
    -0.28
    POSITIVE LOGITS
    Vidite
    0.79
     estekak
    0.73
     Савезне
    0.68
    BeginContext
    0.67
    AndEndTag
    0.66
     Italijanski
    0.65
    ImageContext
    0.63
    DIPSETTING
    0.62
    DoubleQuotes
    0.61
     AssemblyCulture
    0.60
    Act Density 0.147%

    No Known Activations