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

    Neuronpedia

    INDEX
    Explanations

    numbers/statistics over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HD
    -0.08
     ситуацию
    -0.08
     ситуации
    -0.08
    LOGY
    -0.07
    bums
    -0.07
     паз
    -0.07
    HD
    -0.07
    comod
    -0.07
     configs
    -0.07
    Changer
    -0.07
    POSITIVE LOGITS
     waktu
    0.08
    截至
    0.08
     amounted
    0.08
    猛
    0.08
    尼
    0.08
    \S
    0.08
     flattened
    0.07
    去年
    0.07
     Mori
    0.07
     Sina
    0.07
    Act Density 0.103%

    No Known Activations