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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     significant
    0.79
     lav
    0.74
     signific
    0.74
     complex
    0.74
     (“
    0.74
     seemingly
    0.73
     signifikan
    0.73
     neoclassical
    0.73
     adaptation
    0.73
     advocated
    0.72
    POSITIVE LOGITS
    <
    1.76
     <!--
    1.74
    <!--
    1.74
    <div>
    1.57
    </body>
    1.56
    </div>
    1.55
    <!
    1.55
     <
    1.53
     <!--<
    1.51
    <ul>
    1.43
    Act Density 0.165%

    No Known Activations