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

    Neuronpedia

    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    屁
    -0.08
    蹢
    -0.07
    	Spring
    -0.07
    棺
    -0.07
    fragistics
    -0.07
    atio
    -0.06
    备
    -0.06
    	Boolean
    -0.06
    Ⲡ
    -0.06
    Ȥ
    -0.06
    POSITIVE LOGITS
     remodeling
    0.08
    溶液
    0.07
    蔬菜
    0.07
     전혀
    0.07
    anne
    0.07
     hazardous
    0.07
     Vera
    0.07
     wants
    0.07
    (lp
    0.07
    טוב
    0.07
    Act Density 0.003%

    No Known Activations