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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    numbers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.73
     faſt
    -0.71
    httphttps
    -0.68
    +#+#
    -0.67
    SpringRunner
    -0.66
     صوتيه
    -0.66
    RTGC
    -0.65
     ExecuteAsync
    -0.63
    AnchorStyles
    -0.63
     snippetHide
    -0.63
    POSITIVE LOGITS
    .
    0.55
    _
    0.48
    /}.
    0.45
    <bos>
    0.44
    of
    0.43
    }$.
    0.43
    ().
    0.41
    。
    0.40
    |.
    0.40
    прочем
    0.39
    Act Density 0.066%

    No Known Activations