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

    Neuronpedia

    INDEX
    Explanations

    TED Talk topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twinning
    0.61
    да
    0.61
     handball
    0.60
     ჩატი
    0.57
     શિક્ષણ
    0.57
     taxation
    0.56
     प्रशिक्षण
    0.56
    的作用
    0.56
    рга
    0.55
     Dakota
    0.55
    POSITIVE LOGITS
    That
    0.69
    ASH
    0.68
    TED
    0.68
    Q
    0.67
    NO
    0.67
    Ted
    0.66
     infek
    0.64
    NN
    0.63
     on
    0.62
    みんな
    0.62
    Act Density 0.001%

    No Known Activations