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

    Neuronpedia

    INDEX
    Explanations

    say computer related options

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    켭
    -0.07
     Herman
    -0.07
     Comes
    -0.06
    宣
    -0.06
    -function
    -0.06
     childhood
    -0.06
    ◄
    -0.06
    Theme
    -0.06
    ucchini
    -0.06
    inson
    -0.06
    POSITIVE LOGITS
    上线
    0.08
    躺在床上
    0.08
    (filtered
    0.08
     affecting
    0.07
    }`);↵
    0.07
    .RowCount
    0.07
    OfWork
    0.07
    现场
    0.07
    lox
    0.07
    	end
    0.07
    Act Density 0.003%

    No Known Activations