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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ו�
    -0.06
     Treasure
    -0.06
     notation
    -0.06
     Pick
    -0.06
     appreciated
    -0.06
     insightful
    -0.06
    ंजन
    -0.06
     спос
    -0.06
     $('#'
    -0.06
    Excellent
    -0.06
    POSITIVE LOGITS
    _ROT
    0.07
     işe
    0.06
    UARIO
    0.06
     ترکی
    0.06
     trái
    0.06
    -do
    0.06
    -money
    0.06
    роничес
    0.06
    201
    0.06
    ?.
    0.06
    Act Density 0.030%

    No Known Activations