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

    Neuronpedia

    INDEX
    Explanations

    references to variable values or properties in a programming context

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

    dictionary and value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.46
    AndEndTag
    -0.45
     uska
    -0.44
     jScrollPane
    -0.42
     ProtoMessage
    -0.42
     endblock
    -0.41
    
    -0.41
     simplifié
    -0.41
    SizeMode
    -0.41
    SourceChecksum
    -0.40
    POSITIVE LOGITS
     value
    2.78
    value
    2.42
     Value
    2.25
     VALUE
    2.16
    Value
    2.14
     valeur
    2.02
     valore
    1.88
    VALUE
    1.87
     values
    1.81
     waarde
    1.79
    Act Density 0.031%

    No Known Activations