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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᠣ
    -0.08
     הגיע
    -0.07
    什
    -0.07
     расположен
    -0.07
     הממשלה
    -0.07
    哪里
    -0.07
     Ngân
    -0.07
     pcs
    -0.07
    重温
    -0.07
    ".↵↵↵↵
    -0.07
    POSITIVE LOGITS
    偭
    0.08
    thè
    0.07
     controlling
    0.07
    㽏
    0.07
    צועי
    0.06
     наблю
    0.06
    (arg
    0.06
    -to
    0.06
    𝓊
    0.06
    	be
    0.06
    Act Density 0.012%

    No Known Activations