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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Intervention
    -0.06
     Andrew
    -0.06
     Possible
    -0.06
     Digital
    -0.06
    ief
    -0.06
    TREE
    -0.06
     product
    -0.06
     tik
    -0.06
     设置
    -0.06
    beck
    -0.06
    POSITIVE LOGITS
    �
    0.07
     nurt
    0.07
     lands
    0.06
     insufficient
    0.06
    illions
    0.06
     začí
    0.06
    *this
    0.06
    ्वव
    0.06
    ประม
    0.06
    .parseLong
    0.06
    Act Density 0.132%

    No Known Activations