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

    Neuronpedia

    INDEX
    Explanations

    technical terms and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    YA
    0.47
    CAR
    0.47
    Pra
    0.45
    Va
    0.44
    de
    0.43
    Ca
    0.43
    Y
    0.43
    CA
    0.43
    רון
    0.42
    उनकी
    0.41
    POSITIVE LOGITS
     Tayyip
    0.51
     clippings
    0.49
     aplic
    0.48
    পাতালে
    0.47
    长时间
    0.47
     juxtap
    0.46
     Jodi
    0.46
    ීම්
    0.46
     nuove
    0.46
     ឬ
    0.45
    Act Density 0.001%

    No Known Activations