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

    Neuronpedia

    INDEX
    Explanations

    structure-related elements or attributes in coding contexts

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

    tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exteriores
    -0.39
     konusu
    -0.35
     gekomen
    -0.35
     manifestación
    -0.33
     głó
    -0.33
    gemeins
    -0.33
     mogen
    -0.32
    судар
    -0.32
    tapkan
    -0.31
     Tenemos
    -0.31
    POSITIVE LOGITS
    tools
    1.15
     Tools
    1.13
     tools
    1.08
    Tools
    1.07
     TOOLS
    1.04
    Tool
    1.01
    tool
    1.01
    TOOLS
    1.00
    工具
    0.99
     Tool
    0.98
    Act Density 0.004%

    No Known Activations