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

    Neuronpedia

    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite

    finds numeric tokens (years, dates, and other numbers).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     the
    0.45
     an
    0.43
     a
    0.39
     Moscow
    0.35
    NotEmpty
    0.34
     Edinburgh
    0.34
     Scientology
    0.34
    BrNO
    0.34
     的
    0.34
     your
    0.34
    POSITIVE LOGITS
    .
    0.57
    +.
    0.50
    。
    0.49
    ™.
    0.46
     waarbij
    0.46
    .)
    0.45
    .,
    0.44
    ®.
    0.44
    。(
    0.43
    ).
    0.43
    Act Density 0.073%

    No Known Activations