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
    ingular
    -0.06
     detective
    -0.06
     abbreviation
    -0.06
     Indones
    -0.06
    $c
    -0.06
     ner
    -0.06
     wh
    -0.06
    (ix
    -0.06
    (sc
    -0.06
    磁
    -0.06
    POSITIVE LOGITS
    铁
    0.07
    pthread
    0.07
    groundColor
    0.07
    color
    0.07
    iros
    0.06
     sữa
    0.06
     COLOR
    0.06
    yan
    0.06
     jewel
    0.06
    갈
    0.06
    Act Density 0.013%

    No Known Activations