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

    Neuronpedia

    INDEX
    Explanations

    adding or ignoring zeros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பிடித்த
    0.47
     quotas
    0.46
     QR
    0.44
    いたら
    0.43
     доля
    0.43
     quota
    0.43
     haszn
    0.41
     अनुभव
    0.41
     geological
    0.40
     mindre
    0.40
    POSITIVE LOGITS
    Extend
    0.50
    Extended
    0.44
    延伸
    0.42
     Tear
    0.42
    延长
    0.42
     harapan
    0.41
    喈
    0.40
     Extend
    0.40
    ობას
    0.39
    Hemos
    0.39
    Act Density 0.007%

    No Known Activations