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

    Neuronpedia

    INDEX
    Explanations

    EXECUTE PROCEDURE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ست
    0.62
    يك
    0.59
    рата
    0.57
    ше
    0.55
    رم
    0.55
    ના
    0.55
    Ле
    0.54
    ريف
    0.53
    양이
    0.53
    ش
    0.53
    POSITIVE LOGITS
    on
    0.57
    tests
    0.54
    test
    0.54
     artifacts
    0.49
     microarray
    0.49
     cancer
    0.47
    features
    0.47
     annihilation
    0.47
    8
    0.47
    selt
    0.46
    Act Density 0.000%

    No Known Activations