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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಸಾರ್ವಜನಿಕ
    -0.09
     Types
    -0.09
     ಊ
    -0.09
     Ips
    -0.08
     ಜನ
    -0.08
     საზოგადო
    -0.08
     Públic
    -0.08
     pensent
    -0.08
     халыҡ
    -0.08
     δημό
    -0.08
    POSITIVE LOGITS
    狗
    0.16
     dogs
    0.16
    Dog
    0.15
    犬
    0.15
    dog
    0.15
     dog's
    0.14
     dog
    0.14
     狗
    0.14
    dogs
    0.14
    Dogs
    0.14
    Act Density 0.056%

    No Known Activations