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

    Neuronpedia

    INDEX
    Explanations

    integers and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ുകയും
    -0.07
    .ssl
    -0.07
     بابت
    -0.07
     थोड़ा
    -0.07
    Spr
    -0.07
     Apartment
    -0.07
    Volgens
    -0.07
     nesse
    -0.07
    ltf
    -0.07
    ssl
    -0.07
    POSITIVE LOGITS
     Gay
    0.08
     rash
    0.08
     Rally
    0.08
     Tony
    0.08
     namens
    0.08
    胖
    0.08
     interloc
    0.08
     clazz
    0.08
     Romeo
    0.08
     disproportion
    0.08
    Act Density 0.077%

    No Known Activations