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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cast
    -0.07
    ITEM
    -0.07
    Texture
    -0.07
    地方
    -0.07
    长
    -0.07
     ############################################################################
    -0.06
     lugar
    -0.06
    IRROR
    -0.06
    (Group
    -0.06
     ")[
    -0.06
    POSITIVE LOGITS
     обесп
    0.08
     acknowledges
    0.07
     visually
    0.07
    astreet
    0.07
    _firstname
    0.07
     fakt
    0.06
    efa
    0.06
     klar
    0.06
    Ў
    0.06
     propose
    0.06
    Act Density 0.022%

    No Known Activations