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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }}"↵
    -0.07
     Zu
    -0.07
    	pos
    -0.06
     duct
    -0.06
     комнат
    -0.06
    �
    -0.06
     ين
    -0.06
    fak
    -0.06
     маш
    -0.06
     куль
    -0.06
    POSITIVE LOGITS
     سازمان
    0.07
    cej
    0.07
     handled
    0.06
    moz
    0.06
    .Maybe
    0.06
     Εκ
    0.06
    ,string
    0.06
     بازبینی
    0.06
    Sure
    0.06
    (unittest
    0.06
    Act Density 0.001%

    No Known Activations