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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks, particularly commas and quotes

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    special characters and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.77
     $\
    -0.54
    (
    -0.46
     [
    -0.45
    -
    -0.45
    [
    -0.44
     ‘
    -0.43
     a
    -0.43
     (
    -0.42
     under
    -0.42
    POSITIVE LOGITS
    AsUp
    1.17
    IntoConstraints
    1.12
     betweenstory
    1.09
    MessageOf
    1.06
     ویکی‌پدیا
    1.00
     الحره
    0.99
    出版年
    0.98
     myſelf
    0.98
     HasFactory
    0.95
     ainfi
    0.94
    Act Density 0.425%

    No Known Activations