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

    Neuronpedia

    INDEX
    Explanations

    references to licensing and permission-related terms

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

    watermark, com, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.84
    verwijspagina
    -0.79
    LookAnd
    -0.79
    Personendaten
    -0.79
    PreferredItem
    -0.79
    AddTagHelper
    -0.78
    extAlignment
    -0.77
     EconPapers
    -0.77
    setVerticalGroup
    -0.75
    OGND
    -0.74
    POSITIVE LOGITS
     image
    0.27
    ான்
    0.26
     bed
    0.25
    न्न
    0.24
    被
    0.24
     π
    0.24
    amp
    0.23
     Yates
    0.23
    פו
    0.23
    konom
    0.23
    Act Density 0.077%

    No Known Activations