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

    Neuronpedia

    INDEX
    Explanations

    even followed by conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Coronavirus
    0.44
    спублі
    0.43
    UM
    0.42
    ν
    0.42
    NAS
    0.41
    ้ง
    0.41
    hem
    0.41
     ಆರೋಗ್ಯ
    0.41
    お客様
    0.40
    อำ
    0.40
    POSITIVE LOGITS
     tránh
    0.46
     ž
    0.46
     dễ
    0.43
     разделе
    0.43
     منذ
    0.43
     encourage
    0.42
     طريقه
    0.42
     znalaz
    0.42
     ଓ
    0.42
     созда
    0.41
    Act Density 0.007%

    No Known Activations