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

    Neuronpedia

    INDEX
    Explanations

    odi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     politics
    -0.07
     स
    -0.07
    _BACKGROUND
    -0.07
    !!!!!
    -0.06
    ॉ
    -0.06
     Phillip
    -0.06
     software
    -0.06
     있다
    -0.06
    秀
    -0.06
    Void
    -0.06
    POSITIVE LOGITS
    ivi
    0.06
     UAE
    0.06
    .Active
    0.06
    到底
    0.06
     lav
    0.06
    _Server
    0.06
     utrecht
    0.06
    愿
    0.06
     centuries
    0.06
    _co
    0.05
    Act Density 0.006%

    No Known Activations