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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    暾
    -0.08
     hanya
    -0.07
     settling
    -0.07
     conosc
    -0.07
    ?↵↵↵↵↵↵
    -0.07
    性价
    -0.07
     clash
    -0.07
    翦
    -0.07
    新闻记者
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     bestimm
    0.08
    	self
    0.08
     GRA
    0.07
     реб
    0.07
    说了
    0.07
     LEG
    0.06
     Bermuda
    0.06
    chosen
    0.06
     paralle
    0.06
     percept
    0.06
    Act Density 0.013%

    No Known Activations