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

    Neuronpedia

    INDEX
    Explanations

    Aut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bed
    -0.08
    53
    -0.07
    -bed
    -0.07
     блок
    -0.07
    iado
    -0.06
     Cara
    -0.06
     Ideal
    -0.06
    	cc
    -0.06
     Sharia
    -0.06
     Ideally
    -0.06
    POSITIVE LOGITS
     Aut
    0.09
    aut
    0.08
    'aut
    0.07
    autoplay
    0.07
    Aut
    0.07
     AUT
    0.07
     Autumn
    0.07
     Aux
    0.07
    AUT
    0.07
    autocomplete
    0.07
    Act Density 0.074%

    No Known Activations