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

    Neuronpedia

    INDEX
    Explanations

    specifically known or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आपका
    0.50
    비
    0.48
    आपके
    0.46
    录取
    0.46
    у
    0.45
    يكي
    0.45
    후
    0.45
    7
    0.45
    가
    0.44
    फ
    0.43
    POSITIVE LOGITS
    scapes
    0.55
     museums
    0.52
     mesons
    0.52
     dynasties
    0.49
    idän
    0.49
     traditions
    0.49
     prisons
    0.48
     ferns
    0.47
     galaxies
    0.46
     sunflowers
    0.46
    Act Density 0.131%

    No Known Activations