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

    Neuronpedia

    INDEX
    Explanations

    patterns of regular expressions and their variations

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

    `[^` followed by non-`]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Itinerary
    -0.52
     />';
    -0.50
     spreken
    -0.50
     newArray
    -0.48
     idéia
    -0.46
     eccell
    -0.45
    rubin
    -0.45
    ⓧ
    -0.45
    __':
    -0.45
    千里
    -0.44
    POSITIVE LOGITS
    [^
    2.14
    ([^
    1.93
    (.*
    0.78
     unknownFields
    0.71
    (^
    0.58
    (?:
    0.55
     BoxFit
    0.54
    UnknownFields
    0.53
    ([\
    0.51
     (^
    0.49
    Act Density 0.010%

    No Known Activations