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

    Neuronpedia

    INDEX
    Explanations

    negations or statements of denial

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

    Apostrophes followed by certain letters

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.20
    :✨
    -1.17
    +#+#
    -1.15
     EconPapers
    -1.05
    MemoryWarning
    -1.03
     للاسماء
    -0.99
     متعلقه
    -0.97
     ligiloj
    -0.93
    RenderAtEndOf
    -0.91
    Autoritní
    -0.91
    POSITIVE LOGITS
     I
    0.56
    ’
    0.53
     folks
    0.53
    ↵↵
    0.48
     Unfortunately
    0.47
    Unfortunately
    0.46
    <em>
    0.45
     tell
    0.44
    Concer
    0.44
     keber
    0.43
    Act Density 0.102%

    No Known Activations