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

    Neuronpedia

    INDEX
    Explanations

    interest rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æªĶ
    -0.28
     Bieber
    -0.27
     hail
    -0.27
    æ¡£
    -0.27
    ticks
    -0.26
    exels
    -0.26
    _Public
    -0.26
    istic
    -0.26
    entlich
    -0.25
    çļĦåĬ¨ä½ľ
    -0.24
    POSITIVE LOGITS
    æĺ¾çİ°
    0.26
     ("-
    0.26
     poll
    0.25
    among
    0.24
     convenience
    0.24
    åIJ«
    0.24
    Among
    0.23
    æݧèĤ¡èĤ¡ä¸ľ
    0.23
    éĵ¡
    0.23
     pare
    0.23
    Act Density 1.488%

    No Known Activations