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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols in text

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

    html entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.75
    发表于
    -0.65
    endregion
    -0.63
    complexContent
    -0.62
    -------
    -0.62
    脚注の使い方
    -0.59
    featureID
    -0.59
    parsedMessage
    -0.59
    KURZBESCHREIBUNG
    -0.58
     ujednoznacz
    -0.57
    POSITIVE LOGITS
     “
    0.45
    tagHelper
    0.44
     ‘
    0.42
     &#
    0.42
     &
    0.41
    依
    0.38
     â
    0.37
    身
    0.35
    MenuInflater
    0.34
     way
    0.34
    Act Density 0.007%

    No Known Activations