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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or a new section denoted by a specific token

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

    Uncommon initial characters and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    short words ending in gging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boyunca
    -0.48
     duquel
    -0.48
     indipendente
    -0.47
     aceea
    -0.46
     potreb
    -0.45
     kautta
    -0.45
     couverts
    -0.44
     sillä
    -0.43
     yalnız
    -0.42
     recenti
    -0.42
    POSITIVE LOGITS
     препратки
    0.87
     Italijanski
    0.86
     المعيارى
    0.85
    UserScript
    0.83
     الحره
    0.79
    цездатний
    0.78
     nahilalakip
    0.77
    Diwedd
    0.77
     الرياضيه
    0.75
    basicConfig
    0.74
    Act Density 0.047%

    No Known Activations