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

    Neuronpedia

    INDEX
    Explanations

    <|message|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canadians
    -0.09
     Australians
    -0.09
    特点
    -0.08
    NAP
    -0.08
    кот
    -0.08
    看的
    -0.08
    ленные
    -0.08
    šlj
    -0.08
     […]
    -0.08
     realtor
    -0.08
    POSITIVE LOGITS
     reasoning
    0.09
     puzzle
    0.08
    0.08
     cd
    0.08
     medal
    0.08
    0.07
     बत
    0.07
    )↵↵
    0.07
    kal
    0.07
    0.07
    Act Density 0.021%
    No Known Activations