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

    Neuronpedia

    INDEX
    Explanations

    quote that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.47
    )}$,
    0.46
    TAX
    0.43
    인지
    0.40
    User
    0.40
    Ag
    0.39
    Flex
    0.39
     flex
    0.38
    Tax
    0.37
    Philip
    0.37
    POSITIVE LOGITS
    StdHandle
    0.59
     manuscripts
    0.54
     motorcycles
    0.54
     radiographic
    0.52
     coefficients
    0.50
    ič
    0.50
    𒅖
    0.50
     স্থ
    0.49
     radiations
    0.49
     monographs
    0.49
    Act Density 0.004%

    No Known Activations