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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "display
    -0.07
     самого
    -0.07
    ردد
    -0.07
    (sz
    -0.06
    (format
    -0.06
    σμός
    -0.06
     RANGE
    -0.06
    成為
    -0.06
     fulfill
    -0.06
     hlad
    -0.06
    POSITIVE LOGITS
     you
    0.12
     You
    0.08
    you
    0.08
     me
    0.08
    .gz
    0.08
    .You
    0.07
    -you
    0.07
     Bou
    0.07
     us
    0.07
     YOU
    0.06
    Act Density 0.053%

    No Known Activations