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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming metadata and structures in code

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

    programming or configuration

    np_acts-logits-general · gemini-2.0-flash

    programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.93
     يتيمه
    -0.79
    +#+#
    -0.78
    IGraphics
    -0.72
     utafitiHapana
    -0.71
    PostInfinity
    -0.67
    FunctionFlags
    -0.66
    surate
    -0.64
     dourada
    -0.63
     Theſe
    -0.63
    POSITIVE LOGITS
     which
    0.56
     in
    0.47
     on
    0.46
     chain
    0.45
     group
    0.44
    টি
    0.44
     (
    0.44
    ↵↵↵
    0.42
    XmlAccessType
    0.42
    EDEFAULT
    0.41
    Act Density 0.816%

    No Known Activations