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

    Neuronpedia

    INDEX
    Explanations

    describing attributes or specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    勰
    0.46
    oliberal
    0.45
    спользу
    0.42
     dibagi
    0.42
     मांझी
    0.42
    っていました
    0.42
    VELOP
    0.41
     использовали
    0.41
    Ƹ
    0.40
     Drinfeld
    0.40
    POSITIVE LOGITS
     و
    0.43
     وي
    0.42
     персона
    0.40
     tradizione
    0.39
     para
    0.39
    ຸ
    0.39
     tay
    0.39
     futura
    0.38
     discapacidad
    0.38
    renderCamera
    0.38
    Act Density 0.001%

    No Known Activations