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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     due
    -0.07
    (userId
    -0.07
     tercih
    -0.07
     urlencode
    -0.06
    dbus
    -0.06
    api
    -0.06
    .database
    -0.06
     lỗi
    -0.06
    很多
    -0.06
     allegiance
    -0.06
    POSITIVE LOGITS
     ordinal
    0.07
     �
    0.06
     法
    0.06
    лятор
    0.06
    加入
    0.06
     цим
    0.06
    __(↵
    0.06
    ~~~~~~~~
    0.06
    보았다
    0.06
    してい
    0.06
    Act Density 0.006%

    No Known Activations