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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Multiple
    -0.09
    -a
    -0.07
     (*(
    -0.07
     Damage
    -0.07
    %
    -0.07
    _an
    -0.06
     Multiple
    -0.06
    -machine
    -0.06
    AMAGE
    -0.06
    Must
    -0.06
    POSITIVE LOGITS
    DisplayStyle
    0.08
     Yoshi
    0.07
     Externí
    0.07
     ως
    0.07
     vyrá
    0.06
     Influ
    0.06
     Jamie
    0.06
     Census
    0.06
     vyh
    0.06
     환경
    0.06
    Act Density 0.101%

    No Known Activations