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

    Neuronpedia

    INDEX
    Explanations

    programming function definitions and related keywords

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

    code and markup elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wechsel
    -0.29
    Notae
    -0.28
    <?
    -0.28
    //
    -0.27
     Berech
    -0.26
     suaminya
    -0.26
     księ
    -0.26
     Lawton
    -0.25
    /*
    -0.24
    żesz
    -0.24
    POSITIVE LOGITS
    BibitemShut
    0.80
    ConstraintMaker
    0.77
     '\\;'
    0.70
    RenderAtEndOf
    0.70
     Push
    0.68
    OGND
    0.68
    rbrakk
    0.67
     ſind
    0.67
     ddelwed
    0.67
    Bibitem
    0.67
    Act Density 0.001%

    No Known Activations