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

    Neuronpedia

    INDEX
    Explanations

    on the other hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሶ
    0.73
    ূন
    0.64
    されて
    0.62
     udziel
    0.61
    മായി
    0.60
    ֜
    0.59
    Dil
    0.59
    ਾਮ
    0.58
     раз
    0.58
    中的
    0.58
    POSITIVE LOGITS
    另一方面
    2.17
     on
    1.59
    दूसरी
    1.57
     On
    1.52
     Conversely
    1.51
    অন্যদিকে
    1.49
     অন্যদিকে
    1.46
    Conversely
    1.43
    On
    1.42
     दूसरी
    1.41
    Act Density 0.022%

    No Known Activations