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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    outlined
    -0.09
    ancial
    -0.08
     Redistributions
    -0.08
     преимуществ
    -0.08
    pping
    -0.08
    antiated
    -0.08
    atial
    -0.08
     వెల్లడ
    -0.08
     hinsichtlich
    -0.07
    isissez
    -0.07
    POSITIVE LOGITS
     university
    0.09
    卡
    0.09
     academy
    0.08
     отече
    0.08
     הישרא
    0.08
     humorous
    0.08
    UNA
    0.08
     česk
    0.08
    rice
    0.07
    Profesor
    0.07
    Act Density 0.039%

    No Known Activations