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

    Neuronpedia

    INDEX
    Explanations

    does

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     favourite
    -0.07
     nut
    -0.07
    確
    -0.06
     polish
    -0.06
     Wander
    -0.06
    ruption
    -0.06
     cabin
    -0.06
     khô
    -0.06
     featured
    -0.06
     Hồng
    -0.06
    POSITIVE LOGITS
    ोख
    0.07
    DJ
    0.06
     звер
    0.06
     действия
    0.06
    [list
    0.06
     чемпион
    0.06
    ,!
    0.06
     Вер
    0.06
    (dw
    0.06
     discriminatory
    0.06
    Act Density 0.000%

    No Known Activations