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

    Neuronpedia

    INDEX
    Explanations

    PR, APS, Setting, Gemini, abs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HUOBI
    0.42
     टेनिस
    0.42
     لیون
    0.41
    숀
    0.40
    )^{*}
    0.40
     Сер
    0.39
    ">•
    0.39
    Emission
    0.39
    pit
    0.38
    엽
    0.38
    POSITIVE LOGITS
     PR
    0.98
    PR
    0.91
     пра
    0.79
     PRC
    0.76
     PRA
    0.69
    PRS
    0.68
     PRS
    0.68
     pr
    0.67
    pr
    0.67
     PRL
    0.67
    Act Density 0.000%

    No Known Activations