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

    Neuronpedia

    INDEX
    Explanations

    or None/null

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ไม่มี
    0.84
     अवस्था
    0.82
     हालत
    0.80
    未満
    0.79
     fehlt
    0.79
     ทุก
    0.78
     ہونا
    0.78
     arası
    0.77
    ่อน
    0.77
    przy
    0.76
    POSITIVE LOGITS
     nil
    0.81
     either
    0.77
     Nil
    0.70
     appropriate
    0.70
    0.68
     profit
    0.67
     Nothing
    0.67
    0.66
     returns
    0.65
     CURLE
    0.63
    Act Density 0.041%

    No Known Activations