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

    Neuronpedia

    INDEX
    Explanations

    spa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    21
    -0.07
     늘
    -0.07
    ��
    -0.07
    urvey
    -0.07
     Motion
    -0.06
     Therm
    -0.06
    984
    -0.06
     Math
    -0.06
    35
    -0.06
    34
    -0.06
    POSITIVE LOGITS
     Sp
    0.11
     Spencer
    0.10
     Spotify
    0.09
     spotify
    0.09
    ottenham
    0.09
     spur
    0.09
     sp
    0.08
     spouses
    0.08
     Spa
    0.08
    .spi
    0.08
    Act Density 0.049%

    No Known Activations