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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical evaluations or assessments

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

    relating to descriptions or definitions

    np_acts-logits-general · gemini-2.0-flash

    describing things with words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.77
    новниш
    -0.67
     MainAxisSize
    -0.66
    dafx
    -0.65
    Дерекк
    -0.64
    parsedMessage
    -0.64
    лтемелер
    -0.63
    transQ
    -0.62
    featureID
    -0.60
    webElementXpaths
    -0.59
    POSITIVE LOGITS
     phrases
    0.45
     words
    0.45
     phrase
    0.43
     terms
    0.43
     term
    0.40
     descriptions
    0.39
     WORDS
    0.36
     describes
    0.36
     Worte
    0.36
     Wortes
    0.36
    Act Density 0.268%

    No Known Activations