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

    Neuronpedia

    INDEX
    Explanations

    code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -La
    -0.07
    帝王
    -0.07
    HIGH
    -0.07
     эти
    -0.07
     consumed
    -0.07
    泡泡
    -0.07
    produto
    -0.07
    ዓ
    -0.07
    ую
    -0.07
    _FLOW
    -0.07
    POSITIVE LOGITS
     difficulty
    0.06
    ("<
    0.06
    Whenever
    0.06
    <hr
    0.06
     quar
    0.06
    腮
    0.06
     queries
    0.06
    .Red
    0.06
     gcd
    0.06
    쿳
    0.06
    Act Density 0.015%

    No Known Activations