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

    Neuronpedia

    INDEX
    Explanations

    comprehensive introduction, sequence, innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ब
    0.55
     ब
    0.50
     This
    0.46
    हे
    0.45
    ة
    0.45
    '
    0.45
    kw
    0.44
    ND
    0.44
    LO
    0.43
     나
    0.43
    POSITIVE LOGITS
     Gottlieb
    0.52
    isati
    0.48
    Religion
    0.47
    isées
    0.47
    ResponseType
    0.47
     неба
    0.47
    ຂໍ
    0.47
     NEA
    0.46
     Phật
    0.45
     ಔಷಧ
    0.45
    Act Density 0.000%

    No Known Activations