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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and elements related to coding or HTML

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

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    -0.36
    B
    -0.36
     
    -0.33
    1
    -0.33
    2
    -0.33
     législation
    -0.31
    _
    -0.31
    M
    -0.30
        
    -0.30
     orejas
    -0.30
    POSITIVE LOGITS
     ویکی‌پدی
    1.16
    parsedMessage
    1.09
    uxxxx
    1.08
     queſta
    1.04
    niſſe
    1.02
     $_(
    1.00
     Italijanski
    0.96
    iſchen
    0.96
     Chwiliwch
    0.93
    OGND
    0.93
    Act Density 0.001%

    No Known Activations