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

    Neuronpedia

    INDEX
    Explanations

    closing braces and syntax markers in code

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

    closing html/xml tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EditorBrowsable
    -0.53
    ないけど
    -0.50
     navigu
    -0.50
     igång
    -0.50
    陲
    -0.49
     gräns
    -0.49
    ródło
    -0.45
     кӀош
    -0.44
     Junio
    -0.43
     nemlig
    -0.43
    POSITIVE LOGITS
    }</
    1.28
    <bos>
    1.03
    )}</
    0.95
     }</
    0.88
    }}</
    0.85
    ]</
    0.71
    .'</
    0.68
    )</
    0.65
    ?></
    0.63
     ?></
    0.62
    Act Density 0.006%

    No Known Activations