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

    Neuronpedia

    INDEX
    Explanations

    arithmetic and logical operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    breast
    0.42
    romechanical
    0.39
    ﹙
    0.37
    炬
    0.36
    Lastly
    0.36
    astaan
    0.36
    عرف
    0.35
    strong
    0.35
    ेंसिल
    0.34
    Ỷ
    0.34
    POSITIVE LOGITS
     /
    0.83
     //
    0.67
     ;
    0.66
     ->
    0.63
     |
    0.63
     =>
    0.62
    ;
    0.60
     ||
    0.55
     &&
    0.54
     ==>
    0.52
    Act Density 0.110%

    No Known Activations