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

    Neuronpedia

    INDEX
    Explanations

    high-value mathematical or statistical concepts and notations

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

    Followed by "The", "In", "Is", or "How"

    np_acts-logits-general · gemini-2.0-flash

    mathematical or programming queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    -1.00
    <h2>
    -0.89
    ."</
    -0.88
    </h3>
    -0.88
    </h5>
    -0.85
    <h3>
    -0.83
    ''')
    -0.82
    ]]
    -0.80
    </h1>
    -0.79
    </table>
    -0.78
    POSITIVE LOGITS
    <strong>
    0.69
     anledning
    0.66
    <b>
    0.66
     Atlántico
    0.64
     Envío
    0.62
    #######
    0.59
     Electra
    0.58
     republics
    0.58
    vician
    0.57
     صوتيه
    0.56
    Act Density 0.030%

    No Known Activations