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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    들이
    -0.08
    驱
    -0.08
    Artist
    -0.07
    新闻记者
    -0.07
     thermostat
    -0.07
     shaders
    -0.07
     sculpt
    -0.07
    Launcher
    -0.07
     Tôi
    -0.07
     twórc
    -0.07
    POSITIVE LOGITS
    _Last
    0.08
    .coeff
    0.07
    ᗢ
    0.07
    arrays
    0.07
    几个
    0.07
    评分
    0.07
     byte
    0.07
    툼
    0.07
    بات
    0.06
    숟
    0.06
    Act Density 0.022%

    No Known Activations