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

    Neuronpedia

    INDEX
    Explanations

    structured curriculum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nash
    0.50
    N
    0.47
    D
    0.46
    ش
    0.44
     Nash
    0.43
    Nas
    0.43
    X
    0.43
    زاده
    0.42
    SE
    0.42
    Z
    0.41
    POSITIVE LOGITS
    ruits
    0.52
     LiDAR
    0.51
     EBITDA
    0.48
    rainfall
    0.47
    lii
    0.47
    যন্ত্র
    0.47
     fonds
    0.46
     படிக்க
    0.46
     비용
    0.46
    တစ်
    0.46
    Act Density 0.001%

    No Known Activations