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

    Neuronpedia

    INDEX
    Explanations

    internal conflict within group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _packages
    -0.07
     EAST
    -0.07
    .unique
    -0.07
    ันย
    -0.06
    COOKIE
    -0.06
    _Y
    -0.06
     Birliği
    -0.06
     tasarım
    -0.06
     Settlement
    -0.06
     world
    -0.06
    POSITIVE LOGITS
    !).↵↵
    0.06
    cit
    0.06
     обол
    0.06
    �
    0.06
    .BackgroundImageLayout
    0.06
     потер
    0.06
     구매
    0.06
    sx
    0.06
    료
    0.06
    646
    0.05
    Act Density 0.045%

    No Known Activations