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

    Neuronpedia

    INDEX
    Explanations

    in-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shots
    0.71
     crew
    0.67
     Shots
    0.67
     கிர
    0.66
     detailed
    0.65
     waters
    0.64
     স্বাধীনতার
    0.64
    contributors
    0.63
     quick
    0.63
    rafos
    0.63
    POSITIVE LOGITS
     arou
    0.73
    斉
    0.71
    gis
    0.68
     vern
    0.68
     නිසා
    0.67
    徫
    0.65
     кле
    0.64
    Verifier
    0.64
    verify
    0.64
    雱
    0.63
    Act Density 0.001%

    No Known Activations