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

    Neuronpedia

    INDEX
    Explanations

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هِ
    1.11
     puluh
    1.06
     tenfold
    1.06
     exponentially
    1.00
     enumerable
    1.00
     vrste
    1.00
    稍
    1.00
     vastly
    0.99
     हज़ार
    0.97
     நூற்றாண்டில்
    0.95
    POSITIVE LOGITS
    teries
    1.39
    tery
    1.26
    more
    1.19
    ter
    1.13
     more
    1.12
    TERY
    1.04
    씩
    1.02
    क
    1.00
     מאוד
    0.99
    ting
    0.97
    Act Density 0.051%

    No Known Activations