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
    masters
    -0.07
     매매가
    -0.06
     новых
    -0.06
    phies
    -0.06
     ***!↵
    -0.06
     zájem
    -0.06
     phủ
    -0.06
    likle
    -0.06
     Gloss
    -0.06
     술
    -0.06
    POSITIVE LOGITS
     fertil
    0.07
    กต
    0.07
     Educational
    0.06
    -using
    0.06
    married
    0.06
    argar
    0.06
     coupon
    0.06
    *****/↵
    0.06
    지를
    0.06
    ointments
    0.06
    Act Density 0.001%

    No Known Activations