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

    Neuronpedia

    INDEX
    Explanations

    give

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πισ
    -0.09
     malgré
    -0.08
     despite
    -0.08
     draining
    -0.08
     priz
    -0.08
     spite
    -0.07
    Silver
    -0.07
    -coordinate
    -0.07
    -network
    -0.07
     unable
    -0.07
    POSITIVE LOGITS
     unspecified
    0.08
    ત્વ
    0.08
    ydi
    0.08
    ətlər
    0.08
     подраз
    0.08
     Übungen
    0.08
     surname
    0.07
     темы
    0.07
    targets
    0.07
     unclear
    0.07
    Act Density 0.019%

    No Known Activations