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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     birth
    -0.07
     births
    -0.07
     regulators
    -0.06
     stitching
    -0.06
    获得
    -0.06
     blunt
    -0.06
     address
    -0.06
    (outfile
    -0.06
     декабря
    -0.06
     BUFF
    -0.06
    POSITIVE LOGITS
    ="../../../
    0.06
    \Tests
    0.06
    (
↵
    0.06
     {}
↵
↵
    0.06
    _AV
    0.06
    vana
    0.06
     livre
    0.06
     ราค
    0.06
    それは
    0.06
    anna
    0.06
    Act Density 0.006%

    No Known Activations