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

    Neuronpedia

    INDEX
    Explanations

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    合成
    -0.07
    द
    -0.07
    局局长
    -0.07
     ceremon
    -0.07
    ཧ
    -0.07
     nhân
    -0.07
     Scientific
    -0.07
    케
    -0.07
    Team
    -0.07
    .asp
    -0.07
    POSITIVE LOGITS
    register
    0.07
     작은
    0.07
    ORDER
    0.07
    astery
    0.07
    enty
    0.06
    	dst
    0.06
     fc
    0.06
    watch
    0.06
     kişiler
    0.06
    צים
    0.06
    Act Density 0.049%

    No Known Activations