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

    Neuronpedia

    INDEX
    Explanations

    indicators of questions and enumerated lists

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

    Enumerations or lists indicated with numbers

    np_acts-logits-general · gemini-2.0-flash

    list markers like 2) or ii)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]];
    -0.57
    "]));
    -0.51
    ]='
    -0.50
    ')));
    -0.50
    '}),
    -0.48
    ()<<
    -0.48
    ();
    -0.47
    <bos>
    -0.47
    })));
    -0.46
    ()");
    -0.46
    POSITIVE LOGITS
    CppMethod
    0.80
    ఔ
    0.77
    Geplaatst
    0.74
    adaptiveStyles
    0.71
     kaynağından
    0.63
    archiviato
    0.62
    Kedua
    0.62
    aarrggbb
    0.61
    OCCURRED
    0.61
     secondly
    0.60
    Act Density 0.197%

    No Known Activations