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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ️⃣
    1.70
    ة
    1.42
    ⃣
    1.31
    ת
    1.31
    ed
    1.27
    oretically
    1.26
    ت
    1.24
    edics
    1.14
    я
    1.11
    нодоро
    1.09
    POSITIVE LOGITS
    ราะห์
    1.07
    ۔
    1.04
    ริญ
    1.02
    utico
    1.01
    ミス
    1.00
     України
    1.00
     文件
    1.00
    写真
    1.00
     anterior
    0.99
     él
    0.98
    Act Density 0.000%

    No Known Activations