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

    Neuronpedia

    INDEX
    Explanations

    elements related to structure or formatting in data presentation

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

    Code or table delimiters

    np_acts-logits-general · gemini-2.0-flash

    AutomatedReports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.50
    -0.48
    complexContent
    -0.46
    FontOfSize
    -0.43
    CrossRef
    -0.42
     hochzeit
    -0.42
    Lähteet
    -0.42
     kasarigan
    -0.41
     casquette
    -0.41
    expandindo
    -0.40
    POSITIVE LOGITS
     |
    1.60
    |
    1.15
    ｜
    0.90
     |
    0.89
    |\
    0.87
     $|
    0.87
     |\
    0.86
    │
    0.83
    .|
    0.83
    |(
    0.80
    Act Density 0.373%

    No Known Activations