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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to evaluation and reflection on experiences

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

    describing importance and complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.82
    IntoConstraints
    -0.74
    +#+#
    -0.73
    parsedMessage
    -0.69
     Normdatei
    -0.67
    featureID
    -0.67
     للمعارف
    -0.66
    UrlResolution
    -0.66
     للاسماء
    -0.66
    hyrchwyd
    -0.65
    POSITIVE LOGITS
    p
    0.33
    stat
    0.33
      
    0.33
    …
    0.32
    NameInMap
    0.32
     ‘
    0.32
    ‘
    0.31
    „
    0.30
    awn
    0.29
     publicités
    0.29
    Act Density 0.127%

    No Known Activations