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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in code or text

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

    Characters commonly before variable assignments or parameters

    np_acts-logits-general · gemini-2.0-flash

    code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    -0.64
    “
    -0.61
    '
    -0.60
    .
    -0.58
    "
    -0.58
    「
    -0.57
    !
    -0.56
    『
    -0.56
    :
    -0.51
     (
    -0.51
    POSITIVE LOGITS
    ImageContext
    1.28
     etc
    1.18
    +#+#
    1.07
    ~,
    0.99
     *,
    0.99
    aarrggbb
    0.98
    IntoConstraints
    0.98
    *,
    0.96
    etc
    0.94
    **,
    0.90
    Act Density 0.159%

    No Known Activations