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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thor
    -0.08
    áték
    -0.08
    Col
    -0.08
    mdat
    -0.08
     պատասխան
    -0.08
    ‌دهد
    -0.08
    okeo
    -0.08
    Thor
    -0.08
     Col
    -0.07
    agod
    -0.07
    POSITIVE LOGITS
     ولذلك
    0.09
     त्यामुळे
    0.08
     즉
    0.08
     czyli
    0.08
     allowing
    0.08
     hãy
    0.08
     washed
    0.08
     તેથી
    0.08
     découvrez
    0.08
     ergo
    0.08
    Act Density 0.418%

    No Known Activations