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

    Neuronpedia

    INDEX
    Explanations

    parentheses and other punctuation marks, indicating structuring in the text

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

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.39
    ef
    -0.35
    uc
    -0.35
     суще
    -0.34
    ure
    -0.34
    offset
    -0.34
     Weihnachten
    -0.34
    we
    -0.34
     pinulongan
    -0.34
     useful
    -0.33
    POSITIVE LOGITS
    ########.
    0.62
    NUMX
    0.61
    awtextra
    0.60
    oneofs
    0.60
     <<<<<<<<<<<<<<
    0.59
    хьтан
    0.59
    BeginInit
    0.58
    RegistryLite
    0.58
    djangoproject
    0.58
     Normdatei
    0.56
    Act Density 0.006%

    No Known Activations