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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aan
    -0.06
    λικά
    -0.06
    öy
    -0.06
     für
    -0.06
    ăn
    -0.06
     TestData
    -0.06
     zu
    -0.06
     REVIEW
    -0.06
     duas
    -0.06
    qw
    -0.06
    POSITIVE LOGITS
    kommen
    0.07
     HIS
    0.06
    ständ
    0.06
    olesterol
    0.06
    チャ
    0.06
    дяки
    0.06
     Vampire
    0.06
     Wayne
    0.06
     Catholic
    0.06
    �
    0.06
    Act Density 0.010%

    No Known Activations