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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     categorized
    -0.07
     первого
    -0.06
     Tw
    -0.06
    curl
    -0.06
    到了
    -0.06
    觚
    -0.06
    ということで
    -0.06
     الأوسط
    -0.06
     הזאת
    -0.06
     TRE
    -0.06
    POSITIVE LOGITS
     ditch
    0.07
    Spanish
    0.07
     Polic
    0.07
    ades
    0.07
    渔船
    0.07
    ザー
    0.07
    0.06
    nos
    0.06
    ств
    0.06
     stupid
    0.06
    Act Density 0.001%

    No Known Activations