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

    Neuronpedia

    INDEX
    Explanations

    Cam prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.86
    ின்
    1.34
    б
    1.29
    </b>
    1.26
    sch
    1.17
    s
    1.17
    su
    1.16
    д
    1.15
    ์
    1.13
    </h1>
    1.12
    POSITIVE LOGITS
    ご紹介
    1.12
    ő
    1.05
     její
    1.01
    이랑
    1.00
     ي
    0.99
     возможных
    0.98
    មើ
    0.97
    স্পতিবার
    0.97
    رو
    0.96
    ᆹ
    0.96
    Act Density 0.010%

    No Known Activations