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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know" and its variations

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

    who knows or cares

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Familienname
    -0.37
    astify
    -0.36
     InputDecoration
    -0.36
    mengg
    -0.36
     blouse
    -0.35
    KURZBESCHREIBUNG
    -0.35
    ingang
    -0.35
     ringtone
    -0.35
     Slay
    -0.35
     raso
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.58
     knows
    0.54
    HideFlags
    0.52
    iastes
    0.51
     للمعارف
    0.51
    SequentialGroup
    0.51
    anskje
    0.50
    0.50
    knows
    0.50
    harapkan
    0.50
    Act Density 0.003%

    No Known Activations