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

    Neuronpedia

    INDEX
    Explanations

    wanted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ߙ
    -0.08
     releasing
    -0.08
    ++↵
    -0.08
     Carrier
    -0.07
    	fclose
    -0.07
    Inserted
    -0.07
     up
    -0.07
    的支持
    -0.07
    ريف
    -0.07
    alte
    -0.07
    POSITIVE LOGITS
     Goals
    0.08
    瞥
    0.08
     Nicar
    0.08
     Legacy
    0.08
     Situation
    0.08
    之势
    0.07
    同样
    0.07
     Wanted
    0.07
     Fitness
    0.07
     واحدة
    0.07
    Act Density 0.008%

    No Known Activations