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

    Neuronpedia

    INDEX
    Explanations

    tokens that appear frequently in conversational contexts or informal dialogue

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

    HTML or XML tags

    np_acts-logits-general · gemini-2.0-flash

    digits and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.36
    TargetException
    -0.35
    setHorizontal
    -0.35
    TypedDataSet
    -0.35
     ujednoznacz
    -0.35
    UnsafeEnabled
    -0.34
    多少
    -0.34
     doccia
    -0.34
     جذ
    -0.33
     الاطلاع
    -0.33
    POSITIVE LOGITS
    Rüyada
    0.51
     فريبيس
    0.50
    displayquote
    0.49
    ̈́
    0.49
    enumii
    0.47
    CloseOperation
    0.46
    المناصب
    0.46
    Orsay
    0.45
    terase
    0.45
    Personendaten
    0.45
    Act Density 0.619%

    No Known Activations