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

    Neuronpedia

    INDEX
    Explanations

    punctuation and whitespace characters

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

    grammatical particles and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.68
     Италијани
    -0.66
    transQ
    -0.64
     Administrativna
    -0.63
     onCancelled
    -0.63
    ſchen
    -0.62
     Biôgrafia
    -0.61
    adaptiveStyles
    -0.60
    хьтан
    -0.59
    VIAF
    -0.57
    POSITIVE LOGITS
    The
    0.47
    　
    0.47
     
    0.45
     the
    0.42
    As
    0.39
    In
    0.39
    (
    0.37
    When
    0.37
    Since
    0.37
    For
    0.36
    Act Density 0.014%

    No Known Activations