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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the beginning of sentences

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

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.50
    CloseOperation
    -0.50
    TypedDataSet
    -0.47
    webElementXpaths
    -0.46
    tableFuture
    -0.46
    EndGlobal
    -0.45
     BoxDecoration
    -0.44
    DeleteBehavior
    -0.44
    mordial
    -0.43
    variant
    -0.43
    POSITIVE LOGITS
    0.50
     برانيه
    0.46
    jsxFileName
    0.41
     صوتيه
    0.38
     <<<<<<<<<<<<<<
    0.36
    ябре
    0.36
     lenker
    0.35
     kasarigan
    0.35
     kyse
    0.34
     câte
    0.34
    Act Density 0.004%

    No Known Activations