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

    Neuronpedia

    INDEX
    Explanations

    later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chi
    -0.07
    .MediaType
    -0.07
    ाइ
    -0.06
    .isdigit
    -0.06
     ponds
    -0.06
     行政
    -0.06
    "W
    -0.06
    'ét
    -0.06
    拼
    -0.06
    ffmpeg
    -0.06
    POSITIVE LOGITS
     nastav
    0.06
    εργ
    0.06
    arence
    0.06
    outines
    0.06
     tun
    0.06
    uring
    0.06
     khỏ
    0.06
    eth
    0.06
     Illustrated
    0.06
    ön
    0.06
    Act Density 0.002%

    No Known Activations