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

    Neuronpedia

    INDEX
    Explanations

    sign in or sign up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蒉
    0.77
     managable
    0.77
     adduced
    0.72
    বাচক
    0.71
    दूर
    0.70
     manageable
    0.70
     discursive
    0.70
     atmospheres
    0.69
     tolerate
    0.69
     буль
    0.69
    POSITIVE LOGITS
    刺繍
    0.90
     ス
    0.74
     собой
    0.73
    scription
    0.69
     Artist
    0.69
     صلى
    0.68
     मान्य
    0.68
    किसान
    0.67
     Farm
    0.66
    arest
    0.66
    Act Density 0.018%

    No Known Activations