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

    Neuronpedia

    INDEX
    Explanations

    Type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ڬ
    -0.07
    .INFO
    -0.07
    佯
    -0.07
    𝒶
    -0.07
     sequencing
    -0.07
    澽
    -0.06
    দ
    -0.06
    יפור
    -0.06
    ascending
    -0.06
    襁
    -0.06
    POSITIVE LOGITS
     różnych
    0.08
    broker
    0.08
    的主题
    0.07
     Rogers
    0.07
     Jew
    0.07
    ))(
    0.07
    ارية
    0.07
    lösung
    0.07
    *t
    0.07
    born
    0.07
    Act Density 0.004%

    No Known Activations