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

    Neuronpedia

    INDEX
    Explanations

    number followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रेटिंग
    0.43
     duties
    0.43
     razones
    0.43
     Duties
    0.38
     ड्यूटी
    0.38
     കോ
    0.38
    фо
    0.38
    মূলক
    0.37
    Duties
    0.36
    ான
    0.36
    POSITIVE LOGITS
    throw
    0.42
    ष्‍ट
    0.41
     ***
    0.38
    0.38
     Throw
    0.38
    acias
    0.38
     ahli
    0.37
    >"
    0.36
     delf
    0.36
     throw
    0.36
    Act Density 0.004%

    No Known Activations