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

    Neuronpedia

    INDEX
    Explanations

    single or dual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused527>
    0.40
     subsequ
    0.40
    ၏
    0.40
    ujacy
    0.40
    広告
    0.39
    [{}\
    0.39
    اللي
    0.38
    において
    0.38
     tentatively
    0.38
    subMenu
    0.37
    POSITIVE LOGITS
     single
    1.23
     Single
    1.03
    单
    1.02
     double
    1.00
    single
    1.00
    Single
    0.96
    双
    0.89
     SINGLE
    0.88
    SINGLE
    0.87
     dual
    0.84
    Act Density 0.047%

    No Known Activations