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

    Neuronpedia

    INDEX
    Explanations

    references to lists or categories, particularly those with specific notations

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

    of and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.56
    Erreferentziak
    -0.47
    parsedMessage
    -0.47
    Filmografia
    -0.46
     '\\;'
    -0.46
     comprennent
    -0.45
     atrás
    -0.44
    EndInit
    -0.44
     שוליים
    -0.43
    antaranya
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.62
    RenderAtEndOf
    0.50
    LookAnd
    0.45
     Holy
    0.38
    CppCodeGen
    0.38
    noopener
    0.38
    TypeCode
    0.37
     Baker
    0.37
     Jal
    0.36
    ohist
    0.36
    Act Density 0.095%

    No Known Activations