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

    Neuronpedia

    INDEX
    Explanations

    HTML entities and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শ্বরের
    1.57
     rojos
    1.46
     bosses
    1.44
    其他
    1.43
     orada
    1.41
     인한
    1.37
     Alltag
    1.35
     paradise
    1.35
     hitters
    1.31
     kayb
    1.31
    POSITIVE LOGITS
    nbsp
    1.21
    amp
    1.13
    sz
    1.01
    kjav
    1.01
    $\
    1.00
    $("#
    0.99
    $(
    0.97
    <?=
    0.97
    কারে
    0.95
    <%=
    0.95
    Act Density 0.008%

    No Known Activations