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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their works in academic literature

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

    Capital letters followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    authors with initials and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.70
    }>;
    -0.70
    "]:
    -0.68
    rrggbb
    -0.67
    ?>">
    -0.66
    ')):
    -0.63
    Tazama
    -0.63
    })),
    -0.61
    */),
    -0.60
    }}],
    -0.59
    POSITIVE LOGITS
    OGND
    0.51
    ()
    0.48
    {}
    0.47
    (:)
    0.45
     ($)
    0.42
    odles
    0.42
    tonsoft
    0.42
    hawks
    0.41
    <?>
    0.40
    postMessage
    0.40
    Act Density 0.361%

    No Known Activations