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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fname
    -0.08
    消费者
    -0.08
    谁
    -0.08
    UK
    -0.07
     formData
    -0.07
     skyline
    -0.07
    -n
    -0.07
    -billion
    -0.07
     nær
    -0.07
    Lookup
    -0.07
    POSITIVE LOGITS
    щит
    0.07
    го
    0.07
     Может
    0.07
    샏
    0.07
    어야
    0.07
     Hint
    0.06
    뉠
    0.06
    	Input
    0.06
    だったら
    0.06
    -main
    0.06
    Act Density 0.003%

    No Known Activations