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

    Neuronpedia

    INDEX
    Explanations

    jars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⃣
    1.04
    ့
    1.01
    یی
    0.96
    ️⃣
    0.95
    liğini
    0.95
    ින්
    0.92
    𝟎
    0.92
     Siro
    0.91
     Coyote
    0.90
     collider
    0.88
    POSITIVE LOGITS
    '
    1.02
    做
    0.93
    ール
    0.93
    唔
    0.92
    ما
    0.87
    Didn
    0.87
    อื่น
    0.85
    국
    0.85
    的数据
    0.83
    ษัท
    0.82
    Act Density 0.003%

    No Known Activations