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

    Neuronpedia

    INDEX
    Explanations

    grey streaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૃ
    0.37
    ief
    0.37
    tek
    0.36
     Kaw
    0.36
     ثابت
    0.36
    ابر
    0.35
    Nay
    0.35
    nab
    0.35
     paz
    0.35
    Nib
    0.35
    POSITIVE LOGITS
     EXCHANGE
    0.39
    ネス
    0.39
    getpath
    0.39
     checkout
    0.38
     defence
    0.38
     Bldg
    0.38
    échange
    0.38
     आदी
    0.37
    諫
    0.37
     ஏனெ
    0.36
    Act Density 0.004%

    No Known Activations