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

    Neuronpedia

    INDEX
    Explanations

    advocating for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ну
    2.27
    ständig
    2.18
    ness
    2.17
    itories
    2.08
    𝒊
    2.05
    ING
    2.05
    nt
    2.04
    time
    1.99
    희
    1.91
     usersRouter
    1.89
    POSITIVE LOGITS
    ع
    2.48
     کننده
    2.33
    이션
    2.24
    áciu
    2.14
    高
    2.08
    ಾ
    2.06
    ש
    2.06
    ční
    2.05
    aciji
    2.05
    ീ
    2.02
    Act Density 0.971%

    No Known Activations