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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their surrounding context

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

    text/code structural elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cycle
    -0.32
    wives
    -0.32
    ways
    -0.31
     cycling
    -0.31
     without
    -0.31
    cycles
    -0.30
    Cycle
    -0.29
     gider
    -0.29
    gewiesen
    -0.29
     cycles
    -0.28
    POSITIVE LOGITS
     surla
    0.72
    endphp
    0.62
    SequentialGroup
    0.61
     насељу
    0.60
    AndEndTag
    0.58
    XmlAccessorType
    0.57
    ViewFeatures
    0.57
     '\\;'
    0.57
    +:+
    0.56
    ClientSize
    0.56
    Act Density 0.121%

    No Known Activations