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

    Neuronpedia

    INDEX
    Explanations

    ray casting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.50
     che
    0.48
     penalty
    0.48
     penal
    0.47
     embossed
    0.47
     pending
    0.46
     lum
    0.45
    $)
    0.45
     cul
    0.43
     cables
    0.42
    POSITIVE LOGITS
     модерни
    0.53
     Stopwatch
    0.50
    ؟.
    0.49
     મોબ
    0.49
     Purchases
    0.47
    ؟؟
    0.46
    。。
    0.46
     MILK
    0.45
     नवी
    0.44
     பயணி
    0.44
    Act Density 0.002%

    No Known Activations