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
     pretty
    0.62
    //"
    0.62
     precedence
    0.61
     eigenvalue
    0.61
    ।*
    0.61
    ljed
    0.60
     symmetric
    0.60
     forb
    0.59
     decimals
    0.59
     steep
    0.58
    POSITIVE LOGITS
    <
    1.68
     <
    1.63
    <div>
    1.60
    <!
    1.48
     <!--
    1.48
    <body>
    1.47
    </body>
    1.41
    <ul>
    1.40
     <!--<
    1.39
    ,<
    1.33
    Act Density 0.455%

    No Known Activations