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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оза
    -0.07
    -ı
    -0.07
    riors
    -0.06
    loff
    -0.06
    witter
    -0.06
    および
    -0.06
    -Javadoc
    -0.06
    umbnails
    -0.06
    .au
    -0.06
    estyle
    -0.06
    POSITIVE LOGITS
    ایش
    0.07
     Shelley
    0.06
     contain
    0.06
    آخر
    0.06
    	exp
    0.06
     ')
↵
    0.06
     федераль
    0.06
     necklace
    0.06
    !
↵
    0.06
     Excell
    0.06
    Act Density 0.004%

    No Known Activations