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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific formatting characters or whitespace in the text

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

    phone numbers and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.63
    ElementException
    -0.61
     poveznice
    -0.59
    errHandler
    -0.58
    WaitGroup
    -0.56
    AllAfrica
    -0.56
     فريبيس
    -0.56
    setVerticalGroup
    -0.55
    TargetException
    -0.55
    RetentionPolicy
    -0.54
    POSITIVE LOGITS
    engesch
    0.31
    West
    0.29
    keits
    0.28
     držav
    0.27
     West
    0.27
     www
    0.26
     góry
    0.26
     Smoke
    0.26
     Großen
    0.26
     Rad
    0.26
    Act Density 0.034%

    No Known Activations