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

    Neuronpedia

    INDEX
    Explanations

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pathname
    -0.07
     О
    -0.07
     realizing
    -0.06
    国产
    -0.06
     qa
    -0.06
    _ON
    -0.06
    ев
    -0.06
    ойчив
    -0.06
    ходим
    -0.06
     بسیاری
    -0.06
    POSITIVE LOGITS
     　　　
    0.07
    献
    0.07
     臺
    0.06
    .pat
    0.06
     orally
    0.06
     VOL
    0.06
    	logging
    0.06
    ilon
    0.06
     Mult
    0.06
    .Navigation
    0.06
    Act Density 0.022%

    No Known Activations