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

    Neuronpedia

    INDEX
    Explanations

    All about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     allemaal
    0.46
    全体
    0.44
     모두
    0.38
     PROBLEM
    0.36
     HARD
    0.36
     respectivamente
    0.35
    urlpatterns
    0.35
    داری
    0.34
     전체
    0.34
    全体の
    0.34
    POSITIVE LOGITS
     niente
    0.44
    alling
    0.44
     All
    0.43
    igator
    0.42
    compassing
    0.42
     Алла
    0.42
    ழ்த்த
    0.41
    খিল
    0.40
     بیمار
    0.39
    igators
    0.39
    Act Density 0.008%

    No Known Activations