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

    Neuronpedia

    INDEX
    Explanations

    programming and threading-related terms and concepts

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

    code snippets and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yelp
    -0.33
     example
    -0.32
     Stow
    -0.32
    破
    -0.31
     sı
    -0.31
     papier
    -0.31
     Auto
    -0.30
     PIP
    -0.30
    rohr
    -0.30
    Auto
    -0.30
    POSITIVE LOGITS
    urlpatterns
    1.53
     Chwiliwch
    1.01
    setLayoutManager
    0.94
     ToString
    0.86
    setVerticalGroup
    0.84
    IsMutable
    0.84
    AndEndTag
    0.76
    ThroughAttribute
    0.75
     дописавши
    0.74
     NSCoder
    0.74
    Act Density 0.001%

    No Known Activations