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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, conjunctions and some prepositions

    oai_token-act-pair · gemini-2.0-flash

    punctuation and formatting symbols

    np_token-act-pair-logits · gpt-4o-mini

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.83
    .
    -0.47
    by
    -0.46
    for
    -0.44
    too
    -0.41
    apimachinery
    -0.41
    Al
    -0.40
    ，
    -0.40
    \
    -0.40
    Raise
    -0.39
    POSITIVE LOGITS
    "])
    0.85
    %";
    0.77
    ']))
    0.75
    Personendaten
    0.75
    %")
    0.75
    ynnwys
    0.75
    `;
    0.74
    ugeot
    0.72
    Portály
    0.71
     with
    0.70
    Act Density 1.874%

    No Known Activations