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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (location
    -0.06
    億
    -0.06
     od
    -0.06
    �
    -0.06
     steel
    -0.06
     sınav
    -0.06
     noodles
    -0.06
     Hier
    -0.06
    (enemy
    -0.06
    ortal
    -0.06
    POSITIVE LOGITS
     quotes
    0.07
    png
    0.07
    --}}↵
    0.07
    |M
    0.06
    cles
    0.06
    check
    0.06
     صلى
    0.06
    げ
    0.06
     QCOMPARE
    0.06
     incons
    0.06
    Act Density 0.006%

    No Known Activations