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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лиш
    -0.07
     год
    -0.07
     todos
    -0.07
     toddler
    -0.07
     guts
    -0.07
    圣
    -0.07
    ause
    -0.07
    Queue
    -0.07
     Platz
    -0.07
     pixel
    -0.06
    POSITIVE LOGITS
    asia
    0.07
    ẠI
    0.07
    _legal
    0.06
    �
    0.06
     kişinin
    0.06
    ┲
    0.06
    𝙷
    0.06
    𣷭
    0.06
     HY
    0.06
    鳁
    0.06
    Act Density 0.043%

    No Known Activations