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

    Neuronpedia

    INDEX
    Explanations

    references to dictionaries and dictionary-related concepts

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

    dictionary concepts and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \)
    -0.49
    ‐
    -0.48
    出版年
    -0.48
    }{*}{}
    -0.46
    |-
    -0.46
    (!$
    -0.45
    Belf
    -0.43
    Bel
    -0.43
    ”)
    -0.43
    (“
    -0.43
    POSITIVE LOGITS
     dictionary
    2.14
     Dictionary
    1.95
    Dictionary
    1.91
    dictionary
    1.88
     dictionaries
    1.66
     Dictionaries
    1.48
     DICTION
    1.37
     diccionario
    1.33
    字典
    1.30
     dictionnaire
    1.23
    Act Density 0.004%

    No Known Activations