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

    Neuronpedia

    INDEX
    Explanations

    ERT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     오�
    -0.07
    _draw
    -0.07
    分离
    -0.07
    电机
    -0.06
     alas
    -0.06
    汲
    -0.06
    讚
    -0.06
     Areas
    -0.06
    皇子
    -0.06
    엨
    -0.06
    POSITIVE LOGITS
    standing
    0.07
    itecture
    0.07
     wives
    0.07
     Worst
    0.07
    _cross
    0.07
    ности
    0.07
    🕕
    0.07
    frame
    0.06
    嫂
    0.06
    ному
    0.06
    Act Density 0.001%

    No Known Activations