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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    דגש
    -0.09
     wrestler
    -0.07
     hsv
    -0.07
     arou
    -0.07
     compensation
    -0.07
     provincia
    -0.07
    �
    -0.07
    哺乳
    -0.07
    感恩
    -0.07
    为广大
    -0.07
    POSITIVE LOGITS
    싯
    0.07
     Tar
    0.07
    סי
    0.07
     [`
    0.07
    orgen
    0.07
    商业
    0.07
     Source
    0.06
     Adoption
    0.06
    ys
    0.06
     ROOT
    0.06
    Act Density 0.002%

    No Known Activations