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

    Neuronpedia

    INDEX
    Explanations

    numbers in code parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ***",
    0.60
    *****",
    0.53
    %';
    0.53
    %";
    0.51
    mathbf
    0.51
    ู้
    0.51
    히
    0.50
    %",
    0.50
    축
    0.49
    ****",
    0.48
    POSITIVE LOGITS
     ។
    0.71
     （
    0.68
    ](
    0.67
     (.)
    0.64
    jackson
    0.62
    でお
    0.61
     </
    0.60
     తరువాత
    0.60
     McIntyre
    0.60
    startTime
    0.60
    Act Density 2.458%

    No Known Activations