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

    Neuronpedia

    INDEX
    Explanations

    multiple instances of punctuation or formatting characters

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

    code snippets and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.42
    jspb
    -0.41
    Jeografia
    -0.40
     imp
    -0.36
     los
    -0.34
     dit
    -0.34
     lets
    -0.34
     van
    -0.33
    def
    -0.33
    mobileqq
    -0.32
    POSITIVE LOGITS
    expandindo
    0.72
    UnusedPrivate
    0.60
     صوتيه
    0.57
     ujednoznacz
    0.57
     يتيمه
    0.54
     miniaturka
    0.54
    parsedMessage
    0.53
     themſelves
    0.52
     ModelExpression
    0.51
     kasarigan
    0.50
    Act Density 0.001%

    No Known Activations