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

    Neuronpedia

    INDEX
    Explanations

    expressions related to extending or enhancing functionality

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

    extend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     förr
    -0.51
     ModelExpression
    -0.48
     '{@
    -0.44
     BoxFit
    -0.43
     мәкал
    -0.43
    ValueStyle
    -0.42
     مرئيه
    -0.42
    strptime
    -0.42
    Geplaatst
    -0.42
     defaultstate
    -0.42
    POSITIVE LOGITS
     extend
    1.50
     Extend
    1.45
     extended
    1.42
     extension
    1.41
     extending
    1.41
    Extend
    1.36
     Extending
    1.35
    extended
    1.31
     extends
    1.30
     extensions
    1.29
    Act Density 0.067%

    No Known Activations