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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WithTag
    -0.08
    _logging
    -0.08
    ąż
    -0.08
     cánh
    -0.07
    渰
    -0.07
     newbie
    -0.07
    哟
    -0.07
     Catalonia
    -0.07
    暾
    -0.07
    新形势下
    -0.07
    POSITIVE LOGITS
    hazi
    0.08
    となり
    0.07
     ili
    0.07
     hosts
    0.07
    ",[
    0.07
    잏
    0.07
     Km
    0.06
    ]};↵
    0.06
     kötü
    0.06
    conduct
    0.06
    Act Density 0.012%

    No Known Activations