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

    Neuronpedia

    INDEX
    Explanations

    code string substitutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efficient
    -0.08
     fin
    -0.08
     Saf
    -0.07
    ই
    -0.07
     leisurely
    -0.07
     ausência
    -0.07
    ========
    -0.07
     جن
    -0.07
    fin
    -0.07
    -standing
    -0.07
    POSITIVE LOGITS
     જેથી
    0.08
     ताकि
    0.08
     zodat
    0.08
     修
    0.08
     purch
    0.08
     Федера
    0.08
    ，使
    0.07
     leben
    0.07
     ترا
    0.07
    ಿದ್ದರು
    0.07
    Act Density 0.015%

    No Known Activations