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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تحق
    -0.07
     pace
    -0.07
     Nel
    -0.07
    ゥ
    -0.07
                                  ↵
    -0.07
    .examples
    -0.07
    年级
    -0.07
     vücud
    -0.07
    _grp
    -0.07
    ور
    -0.07
    POSITIVE LOGITS
     Jazeera
    0.08
    andest
    0.07
     offshore
    0.07
    🚛
    0.07
     Midnight
    0.07
    篁
    0.07
    	param
    0.07
    하시
    0.07
     "-",
    0.07
    ၊
    0.07
    Act Density 0.008%

    No Known Activations