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

    Neuronpedia

    INDEX
    Explanations

    database commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    号码
    -0.07
    بلغ
    -0.07
    	want
    -0.07
    ูก
    -0.07
    ная
    -0.07
    click
    -0.07
    Knight
    -0.07
     appetite
    -0.07
     butt
    -0.07
    CallBack
    -0.07
    POSITIVE LOGITS
     chooser
    0.07
    (encoder
    0.07
    .Low
    0.06
     majestic
    0.06
     ACE
    0.06
     FilePath
    0.06
     Achie
    0.06
    一个问题
    0.06
    Chooser
    0.06
    efore
    0.06
    Act Density 0.001%

    No Known Activations