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

    Neuronpedia

    INDEX
    Explanations

    Elizabeth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hindi
    -0.08
     Chun
    -0.07
     أف
    -0.07
     carn
    -0.07
    693
    -0.07
     heel
    -0.07
     nen
    -0.07
    舰
    -0.07
    494
    -0.07
    ullets
    -0.06
    POSITIVE LOGITS
     Elizabeth
    0.14
    Elizabeth
    0.12
    abeth
    0.09
     Beth
    0.09
    izabeth
    0.08
    Beth
    0.07
     retry
    0.07
     Smith
    0.07
     Revision
    0.07
    >About
    0.07
    Act Density 0.006%

    No Known Activations