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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adjunct
    -0.08
    .Tab
    -0.08
     Fallen
    -0.07
    .More
    -0.07
    业态
    -0.07
     Attributes
    -0.07
    dbname
    -0.07
     Technology
    -0.07
    基地
    -0.07
    Singleton
    -0.07
    POSITIVE LOGITS
    �
    0.07
    �
    0.07
    ਰ
    0.06
    >--}}↵
    0.06
    리는
    0.06
    }`,↵
    0.06
    ḣ
    0.06
    _views
    0.06
    茶
    0.06
    ◐
    0.06
    Act Density 0.002%

    No Known Activations