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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structures in code

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

    user KurtosisTest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.45
    twimg
    -0.44
    ⓧ
    -0.39
    ImageContext
    -0.39
     HFILL
    -0.38
    HtmlAttribute
    -0.37
    henswürdigkeiten
    -0.36
    <%@
    -0.35
     مُعرِّف
    -0.35
    Спасылкі
    -0.35
    POSITIVE LOGITS
     thunk
    2.81
    thunk
    2.64
    Thunk
    2.53
     thud
    0.88
     thump
    0.74
     Thun
    0.73
     thun
    0.67
     Th
    0.60
     useEffect
    0.57
     Thug
    0.57
    Act Density 0.000%

    No Known Activations