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

    Neuronpedia

    INDEX
    Explanations

    code/mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Run
    -0.06
     zast
    -0.06
     Taken
    -0.06
     здоров
    -0.06
    ,'"
    -0.06
    	done
    -0.06
    \"></
    -0.06
    benh
    -0.06
    	names
    -0.06
    ("---
    -0.06
    POSITIVE LOGITS
    derive
    0.06
    NSUserDefaults
    0.06
    _face
    0.06
     şekilde
    0.06
     trebuie
    0.06
    аты
    0.06
    ár
    0.06
     derive
    0.06
    +.
    0.06
     dolaş
    0.06
    Act Density 0.000%

    No Known Activations