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

    Neuronpedia

    INDEX
    Explanations

    definition of "means"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Е
    0.48
    л
    0.48
    Selected
    0.47
    Australia
    0.46
    by
    0.45
    それ
    0.44
    З
    0.44
    И
    0.44
    ance
    0.43
    AR
    0.43
    POSITIVE LOGITS
    engono
    0.49
    istani
    0.49
    osts
    0.44
     Pillow
    0.43
    స్తుంది
    0.42
    นักงาน
    0.42
     pigmented
    0.42
     `>=
    0.41
     uop
    0.41
    ونا
    0.41
    Act Density 0.002%

    No Known Activations