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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting indicators in a technical or scientific context

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

    mathematical expressions with matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -1.02
     estekak
    -0.96
     autorytatywna
    -0.96
    rrggbb
    -0.93
    parsedMessage
    -0.92
     linkovi
    -0.90
    Билгалдахарш
    -0.88
     propOrder
    -0.88
     الحره
    -0.85
    bootstrapcdn
    -0.84
    POSITIVE LOGITS
    .
    0.35
     suces
    0.34
    3
    0.33
    1
    0.32
     Independencia
    0.31
    Default
    0.31
    2
    0.31
    …
    0.30
     enca
    0.30
     guste
    0.30
    Act Density 0.012%

    No Known Activations