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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recognition
    -0.09
     Recognition
    -0.09
     recognition
    -0.09
     reconhecimento
    -0.08
     régional
    -0.08
    виз
    -0.08
    _GRE
    -0.08
     reconnaître
    -0.08
    ORE
    -0.07
     ветера
    -0.07
    POSITIVE LOGITS
    ărul
    0.07
    ăr
    0.07
    akah
    0.07
    haidh
    0.07
    ؤون
    0.07
     primavera
    0.07
     bordo
    0.07
    婚
    0.07
     Centennial
    0.07
    稿
    0.07
    Act Density 0.002%

    No Known Activations