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

    Neuronpedia

    INDEX
    Explanations

    how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    1.08
    ।
    1.01
    3
    0.87
    льного
    0.84
    سازی
    0.78
    DrvGPIO
    0.74
    。
    0.74
    viridis
    0.73
    ٤
    0.73
     stroked
    0.72
    POSITIVE LOGITS
    ع
    1.51
     as
    1.20
    ம்
    1.16
    ant
    1.13
    א
    0.96
    ό
    0.96
    ون
    0.96
    ות
    0.96
    ac
    0.95
    தி
    0.93
    Act Density 0.529%

    No Known Activations