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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    让
    -0.07
     JOHN
    -0.07
     فارس
    -0.06
    overe
    -0.06
    ुकस
    -0.06
    -ins
    -0.06
     DEAL
    -0.06
     layer
    -0.06
     territorial
    -0.06
    VISION
    -0.06
    POSITIVE LOGITS
     전용
    0.07
    		 ↵
    0.07
     ')↵↵
    0.07
     destek
    0.07
     }}>{
    0.06
     Released
    0.06
    !!}</
    0.06
    >";↵↵
    0.06
    "[
    0.06
    ]--;↵
    0.06
    Act Density 0.033%

    No Known Activations