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

    Neuronpedia

    INDEX
    Explanations

    ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    szer
    1.50
    1.45
     macam
    1.35
    ့်
    1.33
    1.33
    𝗿
    1.32
    𝘆
    1.29
     galima
    1.26
     Möglichkeit
    1.26
    fem
    1.25
    POSITIVE LOGITS
    ERSHIP
    1.64
     sway
    1.42
    یت
    1.25
     aloud
    1.22
     внимания
    1.21
     tịch
    1.19
    পক্ষ
    1.18
    sworth
    1.18
    ख
    1.17
    পক্ষের
    1.15
    Act Density 0.058%

    No Known Activations