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

    Neuronpedia

    INDEX
    Explanations

    olar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reas
    -0.07
    _ing
    -0.07
     키
    -0.06
     مجموع
    -0.06
     الب
    -0.06
    لاث
    -0.06
     Bentley
    -0.06
     zpracování
    -0.06
     मण
    -0.06
    	Y
    -0.06
    POSITIVE LOGITS
     scams
    0.08
    ```
    0.07
    jf
    0.07
    /st
    0.07
    Mailer
    0.06
     đo
    0.06
    £o
    0.06
     ~~
    0.06
     الحل
    0.06
    .pnl
    0.06
    Act Density 0.008%

    No Known Activations