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

    Neuronpedia

    INDEX
    Explanations

    regulatory compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.46
     تطبيق
    0.45
    认证
    0.44
     эксплуа
    0.42
    MiddleLeft
    0.41
    كم
    0.39
    дж
    0.39
    নিবেশ
    0.39
    exploitation
    0.39
    關
    0.39
    POSITIVE LOGITS
     burdens
    0.50
     on
    0.47
     Cornish
    0.46
     dangers
    0.45
     headache
    0.44
     headaches
    0.44
    ӑ
    0.44
     ridd
    0.43
     with
    0.43
     tenté
    0.42
    Act Density 0.005%

    No Known Activations