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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or questioning about something perceived as negative or undesirable

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

    what is this?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.47
    __':
    -0.39
    GEBURTSDATUM
    -0.37
    HasIndex
    -0.37
    RefNanny
    -0.33
     ویکی‌پدیا
    -0.33
    +:+
    -0.33
     stří
    -0.32
     extinción
    -0.30
     affinch
    -0.30
    POSITIVE LOGITS
     utafitiHapana
    0.51
     censiti
    0.51
    tagHelperRunner
    0.49
     strange
    0.49
    WebElementEntity
    0.48
     OFDb
    0.48
    strange
    0.48
    ValueStyle
    0.48
    rungsseite
    0.47
     weird
    0.47
    Act Density 0.066%

    No Known Activations