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

    Neuronpedia

    INDEX
    Explanations

    word choices before Amharic script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phương
    1.29
    ح
    1.23
    拡散
    1.22
    س
    1.22
     ไฟล์
    1.19
    ሱ
    1.18
    ेन
    1.15
     helst
    1.15
     відповід
    1.13
    وشی
    1.13
    POSITIVE LOGITS
     wasn
    1.08
    twisted
    1.02
    ز
    0.99
    miner
    0.96
    )
    0.96
    iv
    0.95
    #$%
    0.94
     didn
    0.94
    Didn
    0.92
    ]。
    0.92
    Act Density 0.001%

    No Known Activations