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

    Neuronpedia

    INDEX
    Explanations

    chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (categories
    -0.07
    ±ط
    -0.06
     high
    -0.06
    ємо
    -0.06
    blocks
    -0.06
    bservice
    -0.06
    ("/{
    -0.06
    _power
    -0.06
    ddb
    -0.06
    /Card
    -0.06
    POSITIVE LOGITS
     Porsche
    0.07
    지원
    0.07
     outlook
    0.06
     McA
    0.06
     horm
    0.06
    .newInstance
    0.06
    _Profile
    0.06
    Ý
    0.06
     Explanation
    0.06
     دع
    0.06
    Act Density 0.034%

    No Known Activations