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

    Neuronpedia

    INDEX
    Explanations

    legal cases/evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curves
    -0.06
     histogram
    -0.06
    博士
    -0.06
     않았
    -0.06
     Holocaust
    -0.06
     فى
    -0.06
    ্�
    -0.06
    률
    -0.06
    운드
    -0.06
     kẻ
    -0.06
    POSITIVE LOGITS
    /password
    0.07
     Locker
    0.06
     elig
    0.06
     donner
    0.06
    �
    0.06
    	document
    0.06
    	GameObject
    0.06
     discriminator
    0.06
     destinationViewController
    0.06
    >");
↵
    0.06
    Act Density 0.094%

    No Known Activations