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

    Neuronpedia

    INDEX
    Explanations

    Rogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     대부분
    -0.07
     fz
    -0.07
     getById
    -0.07
    /tree
    -0.06
    	padding
    -0.06
     ві
    -0.06
     setzen
    -0.06
     gev
    -0.06
     grows
    -0.06
    들과
    -0.06
    POSITIVE LOGITS
     Rogue
    0.07
    mile
    0.07
     Symptoms
    0.07
     impe
    0.07
     rogue
    0.06
    )(*
    0.06
    _Right
    0.06
     rookie
    0.06
    екту
    0.06
     Compet
    0.06
    Act Density 0.001%

    No Known Activations