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

    Neuronpedia

    INDEX
    Explanations

    political organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бюдж
    -0.07
    马丁
    -0.07
    ottom
    -0.07
    俄罗斯
    -0.07
    _SEQ
    -0.07
    成员单位
    -0.07
     seem
    -0.06
    شهور
    -0.06
    סופר
    -0.06
     Bill
    -0.06
    POSITIVE LOGITS
    >E
    0.07
    orary
    0.07
    を持
    0.07
    ">#
    0.07
    (ms
    0.07
    óg
    0.07
     @"\
    0.07
    进取
    0.07
    가
    0.06
    �
    0.06
    Act Density 0.044%

    No Known Activations