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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    够
    -0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
     Diamonds
    -0.06
     bet
    -0.06
     handles
    -0.06
    ods
    -0.06
     sharpen
    -0.06
     western
    -0.06
     seront
    -0.06
    .SE
    -0.06
    POSITIVE LOGITS
    原来
    0.07
     лица
    0.06
     capitalize
    0.06
    сько
    0.06
    hydration
    0.06
    ję
    0.06
    �
    0.06
    mand
    0.06
    prevent
    0.06
    0.06
    Act Density 0.000%

    No Known Activations