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

    Neuronpedia

    INDEX
    Explanations

    in-situ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    们
    1.45
    ak
    1.38
     ẹ
    1.32
    蘆
    1.30
     carbohydrates
    1.28
     dolphins
    1.28
    ist
    1.27
     Φ
    1.27
     tornadoes
    1.26
     acorns
    1.24
    POSITIVE LOGITS
    nment
    1.43
    BTW
    1.38
    taining
    1.37
    ség
    1.27
    जव
    1.26
    nd
    1.25
    tt
    1.23
    usual
    1.23
    EVERY
    1.22
    nm
    1.21
    Act Density 0.002%

    No Known Activations