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

    Neuronpedia

    INDEX
    Explanations

    precision in models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    យ៉
    0.46
    ∓
    0.46
     McKenzie
    0.43
    ៅ
    0.43
     messaging
    0.42
    ئیں۔
    0.42
     लेबल
    0.42
     skew
    0.41
    ždy
    0.41
     Иң
    0.41
    POSITIVE LOGITS
    Excellent
    0.42
    ătoare
    0.42
    Interesting
    0.42
    isca
    0.41
    Artificial
    0.41
     רא
    0.41
     espèce
    0.40
    국
    0.40
    Camera
    0.39
    Offic
    0.39
    Act Density 0.006%

    No Known Activations