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

    Neuronpedia

    INDEX
    Explanations

    cancellations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compute
    -0.08
     theaters
    -0.07
    _RAD
    -0.07
     principalTable
    -0.06
    人员
    -0.06
    	raise
    -0.06
    .serv
    -0.06
    press
    -0.06
    attack
    -0.06
     hottest
    -0.06
    POSITIVE LOGITS
     adı
    0.07
    Đ
    0.06
    "M
    0.06
     Gül
    0.06
     UIApplication
    0.06
    níku
    0.06
    ाठ
    0.06
    approximately
    0.06
     HomeComponent
    0.06
    ibs
    0.06
    Act Density 0.019%

    No Known Activations