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

    Neuronpedia

    INDEX
    Explanations

    nn as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    钠
    0.40
    semester
    0.38
     ආර
    0.37
     toJson
    0.37
    ော်
    0.35
    යා
    0.35
     যাও
    0.35
     semester
    0.35
     wsp
    0.34
     nove
    0.34
    POSITIVE LOGITS
    Ann
    0.40
     fals
    0.39
     bhavanti
    0.38
    Hum
    0.37
    abell
    0.37
    uaries
    0.35
    Natural
    0.35
    ΕΙ
    0.35
     Ann
    0.35
    Ham
    0.35
    Act Density 0.016%

    No Known Activations