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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fi
    -0.07
    goal
    -0.07
    	cmd
    -0.06
    اوی
    -0.06
    Deep
    -0.06
     lacking
    -0.06
     verschill
    -0.06
     sollen
    -0.06
     Jared
    -0.06
    екту
    -0.06
    POSITIVE LOGITS
    ynes
    0.06
    (*
    0.06
     Spir
    0.06
    ")
↵
    0.06
     peny
    0.06
     úplně
    0.06
     Να
    0.06
    ュ
    0.06
    {!!
    0.06
    'on
    0.06
    Act Density 0.004%

    No Known Activations