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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical data

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

    parentheses and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atalos
    -0.43
    Pill
    -0.43
    iddhartha
    -0.41
     pilar
    -0.40
    balleur
    -0.39
     pili
    -0.38
     елның
    -0.38
    GOTREF
    -0.38
    ValueStyle
    -0.37
     LoggerFactory
    -0.36
    POSITIVE LOGITS
     ujednoznacz
    0.56
    IRQn
    0.42
     ब्रेकडाउन
    0.42
     împre
    0.40
     rağmen
    0.40
     <=",
    0.40
    setzungen
    0.39
     Quim
    0.38
    เล
    0.38
     argint
    0.38
    Act Density 0.277%

    No Known Activations