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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Aliases
    -0.08
     attributes
    -0.07
     clk
    -0.07
    istar
    -0.07
     -----↵
    -0.07
     kontrol
    -0.06
     specs
    -0.06
    /tags
    -0.06
     ド
    -0.06
    427
    -0.06
    POSITIVE LOGITS
    _packages
    0.07
    -founder
    0.07
    	iNdEx
    0.06
    (ro
    0.06
     Edwin
    0.06
     власти
    0.06
    ơn
    0.06
    ář
    0.06
    immers
    0.06
    IVER
    0.06
    Act Density 0.522%

    No Known Activations