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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calcul
    -0.07
    %)
    -0.07
     calculation
    -0.07
    会有
    -0.07
    ores
    -0.06
    ื
    -0.06
    .prop
    -0.06
    ТО
    -0.06
     country
    -0.06
    Cog
    -0.06
    POSITIVE LOGITS
     EW
    0.07
    ʖ
    0.07
    wahl
    0.07
     nell
    0.07
     Fleming
    0.07
     Marker
    0.07
    Bow
    0.07
    .pres
    0.07
     hdf
    0.07
     böyle
    0.06
    Act Density 0.017%

    No Known Activations