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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols that indicate space or separation in text

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

    numeric identifiers after labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.59
    Démographie
    -0.40
     useAppContext
    -0.39
    IActionResult
    -0.36
    tuigen
    -0.36
    bindingNavigator
    -0.35
    WaitGroup
    -0.35
    stdio
    -0.35
    -0.35
    ngOn
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.69
     EconPapers
    0.61
     nahilalakip
    0.60
     transfieras
    0.56
     تانيه
    0.55
    AlterField
    0.55
    Personensuche
    0.52
     للمعارف
    0.51
    ')")
    0.51
     שוליים
    0.50
    Act Density 0.002%

    No Known Activations