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

    Neuronpedia

    INDEX
    Explanations

    produce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     covid
    -0.08
     natur
    -0.07
    毳
    -0.07
    Javascript
    -0.07
    就好了
    -0.07
    Eigen
    -0.07
     Ashton
    -0.07
     Abort
    -0.07
    艴
    -0.07
     infix
    -0.07
    POSITIVE LOGITS
     relative
    0.07
    흟
    0.07
    (value
    0.07
    ского
    0.07
    	RT
    0.07
     الإثنين
    0.07
    ользоват
    0.07
     quer
    0.07
    טות
    0.07
     字
    0.07
    Act Density 0.052%

    No Known Activations