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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mum
    -0.06
    (mx
    -0.06
    exels
    -0.06
     segundos
    -0.06
     Roc
    -0.06
    __);↵↵
    -0.06
    	printk
    -0.06
     говорить
    -0.06
     docks
    -0.06
     attitudes
    -0.06
    POSITIVE LOGITS
    _ser
    0.07
    κ
    0.07
     installer
    0.07
    sold
    0.07
    ‌ش
    0.06
    -actions
    0.06
    ћ
    0.06
    он
    0.06
     secretion
    0.06
     puff
    0.06
    Act Density 0.071%

    No Known Activations