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

    Neuronpedia

    INDEX
    Explanations

    Well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的第一个
    -0.08
     Sunderland
    -0.07
     outbreak
    -0.07
     seventeen
    -0.07
     bul
    -0.07
    Ƀ
    -0.07
     beer
    -0.06
     firearms
    -0.06
    ackage
    -0.06
     desperation
    -0.06
    POSITIVE LOGITS
    重要因素
    0.07
    なの
    0.06
     classroom
    0.06
    你好
    0.06
    .virtual
    0.06
    훌
    0.06
    "}}>↵
    0.06
    �
    0.06
    /****************
    0.06
    都非常
    0.06
    Act Density 0.015%

    No Known Activations