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

    Neuronpedia

    INDEX
    Explanations

    code comments and snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hes
    0.38
     غم
    0.35
    囷
    0.34
    :"+
    0.34
    Hes
    0.34
     RasterModelGrid
    0.33
     Polaris
    0.33
     కానీ
    0.33
     హత్య
    0.32
     ++)
    0.32
    POSITIVE LOGITS
    //
    0.36
    <b>
    0.35
     <!--<
    0.33
    #
    0.32
    linked
    0.31
    <!--
    0.31
    cci
    0.29
    譬
    0.29
    inset
    0.29
    <tr>
    0.29
    Act Density 0.001%

    No Known Activations