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

    Neuronpedia

    INDEX
    Explanations

    Connection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ContextHolder
    -0.08
    ปฏ
    -0.07
     обо
    -0.06
    违
    -0.06
    .less
    -0.06
    활
    -0.06
    hb
    -0.06
    搜狐首页
    -0.06
     alleen
    -0.06
    係
    -0.06
    POSITIVE LOGITS
    ！",
    0.08
    ণ
    0.08
     forming
    0.07
           ↵↵
    0.07
    cedure
    0.07
     америк
    0.07
     ?");↵
    0.07
    batis
    0.07
     Securities
    0.07
    机构
    0.07
    Act Density 0.017%

    No Known Activations