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

    Neuronpedia

    INDEX
    Explanations

    numerical and character data related to variables and measurements

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.42
    LabelTagHelper
    -0.36
     ModelExpression
    -0.33
    Diwedd
    -0.33
     inappropriés
    -0.33
    CodedInputStream
    -0.33
     gloire
    -0.32
    libft
    -0.32
     المعيارى
    -0.30
    couvrez
    -0.30
    POSITIVE LOGITS
     ivelany
    0.75
    complexContent
    0.69
    +#+
    0.62
     PeEnEo
    0.57
     CallOverrides
    0.56
     Италијани
    0.54
    Gambas
    0.52
     الرياضيه
    0.51
    matchCondition
    0.51
     Italijanski
    0.49
    Act Density 0.016%

    No Known Activations