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

    Neuronpedia

    INDEX
    Explanations

    non-zero activation values associated with punctuation marks and delimiters

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

    syntax punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.67
    RenderAtEndOf
    -0.61
     المعيارى
    -0.60
    addContainerGap
    -0.59
    mobileqq
    -0.58
     للاسماء
    -0.55
    principalColumn
    -0.55
    oplayer
    -0.53
    addPreferredGap
    -0.52
     pinulongan
    -0.52
    POSITIVE LOGITS
     bits
    0.40
     Spence
    0.36
    Vidite
    0.34
    énd
    0.34
     etc
    0.34
    vestres
    0.33
     따
    0.33
    ("")]
    0.33
    </tfoot>
    0.33
    EqualsAnd
    0.32
    Act Density 0.142%

    No Known Activations