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

    Neuronpedia

    INDEX
    Explanations

    a, say, have sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    反而
    1.03
     ataupun
    0.90
     posteriores
    0.84
    ಿಯೇ
    0.84
    更能
    0.83
    更多
    0.82
     reprise
    0.81
     преодо
    0.81
     moniker
    0.81
     phù
    0.81
    POSITIVE LOGITS
     Suppose
    1.29
    Suppose
    1.28
    XYZ
    1.06
     Sebuah
    1.04
    ABCD
    1.04
     XYZ
    1.04
     ABCD
    1.02
    Scenario
    0.98
    已知
    0.97
     rectangular
    0.96
    Act Density 0.673%

    No Known Activations