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

    Neuronpedia

    INDEX
    Explanations

    brackets or square brackets in the text

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

    code, numbers, variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.62
     )}$
    -0.55
    ))).
    -0.53
     }]
    -0.52
    ')))
    -0.51
    ())))
    -0.50
    })).
    -0.50
     }));
    -0.50
     '.')
    -0.49
    :].
    -0.48
    POSITIVE LOGITS
    [
    1.22
    __[
    0.69
    "][
    0.66
     vectorielle
    0.63
    '][
    0.61
    ()[
    0.60
    _[
    0.60
    [(
    0.59
    [$
    0.59
    [^
    0.58
    Act Density 0.021%

    No Known Activations