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

    Neuronpedia

    INDEX
    Explanations

    Mary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    445
    -0.08
    getStyle
    -0.07
    39
    -0.07
    џN
    -0.07
     Shields
    -0.06
    059
    -0.06
     ==========
    -0.06
    quee
    -0.06
     Chase
    -0.06
    WhatsApp
    -0.06
    POSITIVE LOGITS
     Mary
    0.16
    Mary
    0.13
     Maria
    0.08
     mary
    0.08
    Maria
    0.08
     Maryland
    0.08
     Sarah
    0.08
     Anna
    0.08
    ary
    0.08
     Laura
    0.07
    Act Density 0.010%

    No Known Activations