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

    Neuronpedia

    INDEX
    Explanations

    meta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worn
    -0.07
     bland
    -0.07
     Rice
    -0.06
     Lond
    -0.06
     Folk
    -0.06
     Bud
    -0.06
     zvý
    -0.06
    acağız
    -0.06
    ushort
    -0.06
    การจ
    -0.06
    POSITIVE LOGITS
    Meta
    0.10
     meta
    0.10
    캐
    0.08
     Meta
    0.08
    _meta
    0.08
    as
    0.08
    TRA
    0.08
    _Meta
    0.08
    a
    0.08
    А
    0.07
    Act Density 0.009%

    No Known Activations