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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -",
    -0.07
     nd
    -0.07
    소개
    -0.07
     rover
    -0.06
     Copper
    -0.06
     harass
    -0.06
     Nd
    -0.06
    	code
    -0.06
    Tho
    -0.06
     religion
    -0.06
    POSITIVE LOGITS
    міні
    0.08
     refin
    0.07
    ΕΙ
    0.07
    شر
    0.07
    žil
    0.06
    ุม
    0.06
     мат
    0.06
    ें
    0.06
    unc
    0.06
     الجم
    0.06
    Act Density 0.001%

    No Known Activations