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

    Neuronpedia

    INDEX
    Explanations

    sequences and structures in data representations, particularly with references to items and their attributes

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

    code or structured data delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.01
     صوتيه
    -0.95
    ValueStyle
    -0.92
     パンチラ
    -0.91
    <unused28>
    -0.91
    <unused8>
    -0.91
    <unused16>
    -0.91
    <unused3>
    -0.91
    <pad>
    -0.91
    [@BOS@]
    -0.91
    POSITIVE LOGITS
    0.30
    .
    0.29
    [
    0.29
        
    0.29
     Instead
    0.28
     diferente
    0.28
    @
    0.28
     по
    0.27
     instead
    0.27
    ↵
    0.27
    Act Density 0.129%

    No Known Activations