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

    Neuronpedia

    INDEX
    Explanations

    code snippets and structure definitions in programming languages

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code blocks and null values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.88
    ftagPool
    -0.84
    NewUrlParser
    -0.84
    +#+#
    -0.82
    rungsseite
    -0.80
    oa̍t
    -0.78
     виправивши
    -0.72
    typeorm
    -0.68
     للمعارف
    -0.68
    tagHelperRunner
    -0.67
    POSITIVE LOGITS
     null
    1.86
     nothing
    1.76
     None
    1.72
    null
    1.69
    None
    1.67
     nil
    1.59
     none
    1.54
     Nothing
    1.51
     NULL
    1.50
    Nothing
    1.50
    Act Density 0.698%

    No Known Activations