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

    Neuronpedia

    INDEX
    Explanations

    punctuation or the presence of commas

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

    listing Chinese punctuation and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.75
    SharedCtor
    -0.70
     Houſe
    -0.68
     feroit
    -0.61
     Majefty
    -0.60
     maș
    -0.60
    +#+#
    -0.59
     wireType
    -0.59
     BoxDecoration
    -0.59
     noDo
    -0.57
    POSITIVE LOGITS
    、
    1.03
    ）、
    0.71
    )、
    0.70
     、
    0.69
    」、
    0.66
    』、
    0.59
    ،
    0.50
    بوابة
    0.48
    、《
    0.47
    、「
    0.46
    Act Density 0.001%

    No Known Activations