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

    Neuronpedia

    INDEX
    Explanations

    seemingly random sequences of characters, possibly related to IDs or codes

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
      
    -0.71
    </strong>
    -0.70
     
    -0.66
    ’
    -0.65
    1
    -0.64
    ↵
    -0.64
    <strong>
    -0.63
    2
    -0.62
    ↵↵
    -0.61
     G
    -0.61
    POSITIVE LOGITS
    parsedMessage
    1.69
     betweenstory
    1.67
    RenderAtEndOf
    1.66
     مشين
    1.63
     tartalomajánló
    1.60
    AddTagHelper
    1.59
    ValueStyle
    1.58
     дописавши
    1.54
     autorytatywna
    1.53
    LookAnd
    1.49
    Act Density 2.330%

    No Known Activations