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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     niezbędn
    -0.07
    סמ
    -0.07
    运算
    -0.07
    下来
    -0.07
    פעולות
    -0.07
    𝜃
    -0.07
    מלא
    -0.07
     б
    -0.07
    -↵↵
    -0.07
    了下来
    -0.06
    POSITIVE LOGITS
    邮政
    0.08
     races
    0.07
    trieve
    0.07
    userinfo
    0.06
    ﭶ
    0.06
     trout
    0.06
     Rubber
    0.06
    ⤶
    0.06
    VIC
    0.06
    鹃
    0.06
    Act Density 0.005%

    No Known Activations