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

    Neuronpedia

    INDEX
    Explanations

    subarrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Indicates
    0.48
     indicates
    0.43
     noise
    0.42
     இருந்தது
    0.40
     ছিল
    0.40
     greenery
    0.39
    可能です
    0.38
     दिखा
    0.38
     below
    0.37
    vidia
    0.37
    POSITIVE LOGITS
    ige
    0.42
    isser
    0.41
    razione
    0.41
    ripty
    0.41
     cloned
    0.40
     공부해
    0.39
    発展
    0.39
     clon
    0.38
    ologie
    0.38
     многи
    0.38
    Act Density 0.000%

    No Known Activations