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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dior
    0.49
     미리
    0.48
     совокуп
    0.48
     Đoàn
    0.46
    試し
    0.46
    実際の
    0.45
    事前
    0.45
     साकार
    0.44
     പറയുന്നത്
    0.44
     wypeł
    0.44
    POSITIVE LOGITS
     zaidi
    0.43
     increased
    0.42
    ieren
    0.40
    ugia
    0.39
     null
    0.38
    inet
    0.38
    uyendo
    0.38
    效率
    0.38
     Fehler
    0.37
     yt
    0.37
    Act Density 0.002%

    No Known Activations