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

    Neuronpedia

    INDEX
    Explanations

    say on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     באופן
    -0.07
     compare
    -0.07
     todo
    -0.07
    ListView
    -0.07
     viewType
    -0.07
    	JPanel
    -0.07
    成年人
    -0.07
    嘿嘿
    -0.07
     Spartan
    -0.06
    (nums
    -0.06
    POSITIVE LOGITS
    Rent
    0.07
     ---↵
    0.07
    _HIDDEN
    0.07
     Age
    0.06
    --;↵↵
    0.06
    IL
    0.06
    logy
    0.06
    ."↵↵
    0.06
    ist
    0.06
     Staff
    0.06
    Act Density 0.052%

    No Known Activations