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

    Neuronpedia

    INDEX
    Explanations

    references to package names in a programming context

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

    java package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.91
     ***!
    -0.64
    package
    -0.62
    tvguidetime
    -0.59
    StoryboardSegue
    -0.57
    UrlResolution
    -0.56
    IntoConstraints
    -0.54
    verifyException
    -0.54
    afficheront
    -0.52
     ModelExpression
    -0.50
    POSITIVE LOGITS
     org
    0.53
    org
    0.52
     arşivlendi
    0.46
     com
    0.45
    lieu
    0.44
    brokes
    0.41
    tits
    0.40
     trib
    0.40
     ORG
    0.40
    ork
    0.39
    Act Density 0.003%

    No Known Activations