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

    Neuronpedia

    INDEX
    Explanations

    sports achievements and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    0.51
     S
    0.47
     bill
    0.45
     agricultura
    0.45
     t
    0.44
     R
    0.44
     artesan
    0.43
     ಇ
    0.43
     ankaŭ
    0.42
    S
    0.42
    POSITIVE LOGITS
    стом
    0.43
     maestros
    0.42
    ском
    0.41
    스트
    0.40
     salaried
    0.40
    зму
    0.40
    льский
    0.39
     함수의
    0.39
    ૨
    0.39
     జట్టు
    0.39
    Act Density 0.043%

    No Known Activations