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

    Neuronpedia

    INDEX
    Explanations

    test cases and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কেরা
    0.42
    Unless
    0.40
     unless
    0.39
    どの
    0.39
    <u>
    0.38
    OTA
    0.38
    ota
    0.38
    ęp
    0.38
    unless
    0.37
     nào
    0.37
    POSITIVE LOGITS
     테스트
    0.64
     mixed
    0.63
     testen
    0.63
    测试
    0.62
     case
    0.60
    測試
    0.60
     testing
    0.59
     teste
    0.59
     waarbij
    0.59
     mehrere
    0.58
    Act Density 0.024%

    No Known Activations