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

    Neuronpedia

    INDEX
    Explanations

    given information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    োয়
    0.71
    erné
    0.63
     hijas
    0.63
    रावर
    0.63
     страниц
    0.63
    cheid
    0.62
    व्
    0.60
     домой
    0.60
     やっぱり
    0.59
     обов
    0.58
    POSITIVE LOGITS
     given
    4.51
    given
    3.98
     provided
    3.97
     Given
    3.71
    Given
    3.70
    provided
    3.45
     diberikan
    3.37
     Provided
    3.31
     supplied
    3.29
    Provided
    3.16
    Act Density 2.140%

    No Known Activations