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

    Neuronpedia

    INDEX
    Explanations

    McG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zi
    -0.08
    联
    -0.07
    			 ↵
    -0.07
    влажн
    -0.07
    remen
    -0.07
    タイプ
    -0.07
             
↵
    -0.07
    給
    -0.07
        		↵
    -0.07
     Jiang
    -0.07
    POSITIVE LOGITS
     המס
    0.08
    。（
    0.07
    .shortcuts
    0.07
    细则
    0.07
     бю
    0.07
     menus
    0.07
    _table
    0.07
    =\"$
    0.07
     McG
    0.07
     grues
    0.07
    Act Density 0.011%

    No Known Activations