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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting elements commonly associated with programming code or scripts

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

    code and programming structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zional
    -0.35
    stddef
    -0.34
     nimic
    -0.33
    olutamente
    -0.32
    Stdout
    -0.32
     extensive
    -0.32
     kandungan
    -0.32
     Zeich
    -0.31
     locked
    -0.31
     newcomers
    -0.31
    POSITIVE LOGITS
    GEBURTSDATUM
    0.70
    Autoritní
    0.65
     يتيمه
    0.63
    transQ
    0.58
    httphttps
    0.57
    DeleteBehavior
    0.57
    enumi
    0.56
    ValueStyle
    0.56
    الحياه
    0.55
    MessageTagHelper
    0.53
    Act Density 0.077%

    No Known Activations