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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

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

    punctuation and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뀔
    -0.42
    CppMethod
    -0.41
     limiting
    -0.39
     Hol
    -0.39
     propOrder
    -0.38
     AssemblyCulture
    -0.38
    +#+
    -0.35
    Hol
    -0.35
     hol
    -0.35
    limiting
    -0.34
    POSITIVE LOGITS
    Derbyniad
    0.57
     queſta
    0.54
    0.53
     šaty
    0.52
     enfans
    0.51
     dieux
    0.50
    URBANA
    0.50
    annuation
    0.50
    Rujuakan
    0.49
    Autoritní
    0.49
    Act Density 0.031%

    No Known Activations