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

    Neuronpedia

    INDEX
    Explanations

    output should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     非
    -0.07
    	fire
    -0.07
     spawn
    -0.07
     regions
    -0.06
    packing
    -0.06
    -help
    -0.06
    -position
    -0.06
    254
    -0.06
    def
    -0.06
    Ash
    -0.06
    POSITIVE LOGITS
    0.06
    0.06
    ensburg
    0.06
     بشكل
    0.06
     сильно
    0.06
    统
    0.06
     pł
    0.06
    *a
    0.06
    _COMPILE
    0.06
     auss
    0.06
    Act Density 0.024%

    No Known Activations