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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .warning
    -0.07
     Bake
    -0.07
    .Bl
    -0.07
    讲师
    -0.07
     releg
    -0.07
     traveller
    -0.07
    暗示
    -0.07
    ี้
    -0.07
     CNC
    -0.07
    abr
    -0.07
    POSITIVE LOGITS
     out
    0.07
    䴙
    0.06
    ”?
    0.06
    yard
    0.06
    엘
    0.06
     harb
    0.06
    נט
    0.06
    (sock
    0.06
    בית
    0.06
     пот
    0.06
    Act Density 0.019%

    No Known Activations