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

    Neuronpedia

    INDEX
    Explanations

    URLs and website links

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

    URLs ending in a suffix

    np_acts-logits-general · gemini-2.0-flash

    urls and websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.03
    Personendaten
    -1.00
    脚注の使い方
    -1.00
    ']")
    -0.96
     '\\;'
    -0.96
     мәкал
    -0.94
    LookAnd
    -0.93
    تقاوى
    -0.92
    ']):
    -0.91
    Personensuche
    -0.91
    POSITIVE LOGITS
    www
    0.62
     www
    0.61
    </em>
    0.58
    @
    0.58
    #
    0.43
     website
    0.42
     genitori
    0.41
    ://
    0.41
     giustizia
    0.41
     .
    0.41
    Act Density 0.153%

    No Known Activations