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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their organization within a dataset

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

    Numbers and exponents in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    seven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QMetaType
    -0.72
     postIndex
    -0.60
     doInBackground
    -0.59
     الرياضيه
    -0.56
     كومونز
    -0.55
    Personendaten
    -0.54
     peroxidase
    -0.53
    addCriterion
    -0.53
    opor
    -0.52
    gable
    -0.52
    POSITIVE LOGITS
    7
    0.83
     seven
    0.70
     seventh
    0.70
     VII
    0.65
     tujuh
    0.62
     Seven
    0.61
     seventy
    0.59
     Seventy
    0.58
    VII
    0.58
    seven
    0.57
    Act Density 0.595%

    No Known Activations