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

    Neuronpedia

    INDEX
    Explanations

    drawing, imaging, flo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喁
    0.49
    柺
    0.46
    FRAMERATE
    0.46
    闓
    0.46
    Bathroom
    0.45
     ⏮
    0.44
     Kavan
    0.43
    訢
    0.43
    办事
    0.43
     Distortion
    0.41
    POSITIVE LOGITS
     }:
    0.40
    ":
    0.39
    }:
    0.39
    >.
    0.37
    偷
    0.36
    die
    0.35
    chec
    0.34
    }_{\
    0.33
     là
    0.33
     जाणार
    0.32
    Act Density 0.001%

    No Known Activations