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

    Neuronpedia

    INDEX
    Explanations

    necessity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    طب
    -0.07
    [iVar
    -0.07
    уча
    -0.07
     itu
    -0.07
     Kub
    -0.07
     estad
    -0.06
    icip
    -0.06
     Disorder
    -0.06
     uluslararası
    -0.06
     servidor
    -0.06
    POSITIVE LOGITS
    	ll
    0.09
    的缘故
    0.07
    סתר
    0.07
    逑
    0.07
    晚期
    0.07
    ¯¯¯¯
    0.07
    Dependencies
    0.06
    REAT
    0.06
     Brief
    0.06
    COMM
    0.06
    Act Density 0.184%

    No Known Activations