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

    Neuronpedia

    INDEX
    Explanations

    AI property definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ত্রি
    0.40
    evaluate
    0.39
    ét
    0.39
    ovid
    0.39
     pageWidth
    0.39
    წყვე
    0.38
    Maxwell
    0.38
    avit
    0.38
     belirtti
    0.38
    compareTo
    0.38
    POSITIVE LOGITS
     property
    0.47
    ͚
    0.39
     Property
    0.38
    property
    0.37
     свойства
    0.37
     propiedad
    0.36
    Property
    0.36
     terminology
    0.36
     imitated
    0.36
    属性
    0.36
    Act Density 0.001%

    No Known Activations