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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grac
    -0.06
     overseas
    -0.06
     ***
    -0.06
    (padding
    -0.06
     Goose
    -0.06
    :-
    -0.06
     granny
    -0.06
    $url
    -0.06
     manten
    -0.06
     On
    -0.06
    POSITIVE LOGITS
     tidak
    0.06
    Math
    0.06
     Mash
    0.06
    upplier
    0.06
     Pelosi
    0.06
     Compet
    0.06
    	Int
    0.06
    407
    0.06
    atie
    0.06
     치
    0.06
    Act Density 0.030%

    No Known Activations