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

    Neuronpedia

    INDEX
    Explanations

    Business operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     పేర్క
    -0.09
     തന്നെ
    -0.09
     seguida
    -0.08
     [(
    -0.08
    аста
    -0.08
    ­der
    -0.08
     खास
    -0.08
     ас
    -0.08
     vasta
    -0.08
     pár
    -0.07
    POSITIVE LOGITS
    UC
    0.09
    Yo
    0.08
    _management
    0.08
    yo
    0.07
    怎么
    0.07
    brevi
    0.07
     brochure
    0.07
    について
    0.07
     أبي
    0.07
    Bloc
    0.07
    Act Density 0.249%

    No Known Activations