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

    Neuronpedia

    INDEX
    Explanations

    special symbols and formatting used in code or markup languages

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    special characters followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.84
    (
    -0.53
    <eos>
    -0.48
     sure
    -0.48
    ↵↵
    -0.48
    The
    -0.47
    providedIn
    -0.46
     no
    -0.45
    <u>
    -0.44
    [
    -0.43
    POSITIVE LOGITS
    AsUp
    0.92
     betweenstory
    0.89
    CloseOperation
    0.89
    elemField
    0.88
    تقاوى
    0.87
    :✨
    0.84
     >=",
    0.83
    jsonwebtoken
    0.82
    WithIOException
    0.81
    ArrowToggle
    0.81
    Act Density 1.178%

    No Known Activations