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

    Neuronpedia

    INDEX
    Explanations

    Citation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tel
    -0.08
    /rem
    -0.08
    仿佛
    -0.08
    IME
    -0.08
     bask
    -0.07
    Ķ
    -0.07
    _DH
    -0.07
    KB
    -0.07
    Sl
    -0.07
    Desc
    -0.07
    POSITIVE LOGITS
    宋体
    0.07
    ))/
    0.07
     Copper
    0.07
     ]);
    0.07
    谷爱
    0.07
    ива
    0.07
    dup
    0.07
    工作经验
    0.07
    "]);↵
    0.07
    复工复
    0.06
    Act Density 0.009%

    No Known Activations