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

    Neuronpedia

    INDEX
    Explanations

    breakdown of explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meski
    0.48
     özellikle
    0.43
     incluem
    0.43
     insbesondere
    0.43
     posebno
    0.42
     xviii
    0.41
     சிவன்
    0.40
     細胞
    0.40
    🙏🏻
    0.40
     Özellikle
    0.40
    POSITIVE LOGITS
    /
    0.45
    /$
    0.42
     কিংবা
    0.39
    <0x80>
    0.37
     অথবা
    0.37
     أو
    0.37
    রা
    0.36
    或
    0.35
    或者
    0.34
    urement
    0.33
    Act Density 0.101%

    No Known Activations