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

    Neuronpedia

    INDEX
    Explanations

    snap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ลาน
    -0.08
    みて
    -0.08
    ID
    -0.08
    _begin
    -0.08
    untime
    -0.08
    较多
    -0.07
    Alice
    -0.07
    乐队
    -0.07
    出资
    -0.07
     اللقاء
    -0.07
    POSITIVE LOGITS
    బ
    0.07
    畸
    0.07
     Росс
    0.07
    /met
    0.07
    ﳎ
    0.07
    كهرب
    0.06
    布置
    0.06
    齒
    0.06
     appliance
    0.06
    �
    0.06
    Act Density 0.006%

    No Known Activations