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

    Neuronpedia

    INDEX
    Explanations

    mathematics problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     â
    -0.09
     pause
    -0.08
     legacy
    -0.08
    Â
    -0.07
     lingering
    -0.07
     junk
    -0.07
     ï
    -0.07
     parr
    -0.07
    _BL
    -0.07
     paused
    -0.07
    POSITIVE LOGITS
     सूत्र
    0.09
     जैसा
    0.09
    teachers
    0.08
    શું
    0.08
    wegen
    0.08
     conséquent
    0.08
     όπως
    0.08
    क्या
    0.08
     coupling
    0.08
    vær
    0.08
    Act Density 0.132%

    No Known Activations