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

    Neuronpedia

    INDEX
    Explanations

    shake well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рып
    0.44
    0.41
    лизова
    0.40
    ěji
    0.40
     आ
    0.39
    ipation
    0.38
    কৃত
    0.38
     উপকার
    0.38
    之上
    0.38
     occupa
    0.37
    POSITIVE LOGITS
    CUT
    0.43
    Cut
    0.41
     References
    0.41
    Seed
    0.40
    Agr
    0.39
    BAB
    0.38
    Mold
    0.38
    Robot
    0.38
    India
    0.38
     reich
    0.38
    Act Density 0.000%

    No Known Activations