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

    Neuronpedia

    INDEX
    Explanations

    1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ുവ
    1.05
    ון
    0.96
    いろんな
    0.94
     частина
    0.92
     Роз
    0.91
    দারি
    0.87
     dục
    0.84
    swedish
    0.83
    पत्रिका
    0.83
     особи
    0.82
    POSITIVE LOGITS
    u
    1.32
    er
    1.27
    ا
    1.24
    ení
    1.17
    ри
    1.08
    ../
    1.05
     prioritise
    1.02
    uits
    1.02
    r
    1.00
    uose
    0.97
    Act Density 0.001%

    No Known Activations