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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    梗
    -0.08
     seamlessly
    -0.07
     citing
    -0.07
    !’
    -0.07
    =".$
    -0.07
     meetup
    -0.07
    层级
    -0.07
     ومن
    -0.07
    ⚐
    -0.06
     Sight
    -0.06
    POSITIVE LOGITS
    sequelize
    0.08
    zel
    0.08
    BarItem
    0.08
    abez
    0.08
    ovich
    0.07
    鹣
    0.07
    POS
    0.07
    avery
    0.07
    Gram
    0.07
    乔治
    0.07
    Act Density 0.007%

    No Known Activations