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

    Neuronpedia

    INDEX
    Explanations

    symbols or patterns indicating structured data formats

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

    request headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
    TargetException
    -0.50
     afgelopen
    -0.49
     initView
    -0.47
    RegressionTest
    -0.46
    drawSprites
    -0.46
     vrijwilli
    -0.44
     Berührung
    -0.41
    ContextCompat
    -0.38
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.59
     Favourite
    0.52
     ModelExpression
    0.51
    ']['
    0.50
     &___
    0.49
     createState
    0.46
    AddRef
    0.46
    ConstraintMaker
    0.45
     hostess
    0.45
    angliski
    0.45
    Act Density 0.019%

    No Known Activations