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

    Neuronpedia

    INDEX
    Explanations

    week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concession
    -0.07
    endir
    -0.07
    ادل
    -0.07
    aires
    -0.06
    .restart
    -0.06
     cones
    -0.06
     peeled
    -0.06
     вис
    -0.06
    १�
    -0.06
     cavalry
    -0.06
    POSITIVE LOGITS
     week
    0.07
    .promise
    0.07
     diverse
    0.06
    眉
    0.06
    .aggregate
    0.06
     initialValue
    0.06
     •
    0.06
    ,exports
    0.06
     month
    0.06
    药
    0.06
    Act Density 0.014%

    No Known Activations