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

    Neuronpedia

    INDEX
    Explanations

    array in code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㬶
    0.43
    ровая
    0.42
     setTimeout
    0.41
    SafeArea
    0.39
    ReturnValue
    0.39
     организация
    0.39
    ोसी
    0.39
    Agregar
    0.39
    Handle
    0.38
    Если
    0.38
    POSITIVE LOGITS
     ber
    0.43
     hus
    0.39
    reactive
    0.39
     listy
    0.37
     Trop
    0.37
     መድ
    0.36
     свойств
    0.36
     bir
    0.35
     list
    0.35
    <-
    0.35
    Act Density 0.002%

    No Known Activations