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

    Neuronpedia

    INDEX
    Explanations

    quotes/quoted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     розвитку
    -0.07
    Payload
    -0.06
     выбра
    -0.06
    غراف
    -0.06
    -arm
    -0.06
    	va
    -0.06
     美国
    -0.06
     حسین
    -0.06
    -angle
    -0.06
    className
    -0.06
    POSITIVE LOGITS
    Media
    0.07
     repeated
    0.07
     Tomas
    0.07
    ')
↵
↵
    0.06
    MSN
    0.06
     """
↵
    0.06
    ("""↵
    0.06
    ono
    0.06
     |↵↵
    0.06
    idor
    0.06
    Act Density 0.009%

    No Known Activations