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

    Neuronpedia

    INDEX
    Explanations

    Code properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aos
    -0.07
     liquid
    -0.07
    _L
    -0.07
     Meadows
    -0.06
    y
    -0.06
     abandonment
    -0.06
    める
    -0.06
    сих
    -0.06
    osit
    -0.06
    روف
    -0.06
    POSITIVE LOGITS
    (save
    0.07
    advertisement
    0.07
    ``↵
    0.06
    .rollback
    0.06
    $results
    0.06
    //
↵
    0.06
     течение
    0.06
     secular
    0.06
    �
    0.06
    	exit
    0.06
    Act Density 0.054%

    No Known Activations