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

    Neuronpedia

    INDEX
    Explanations

    people or roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    okrat
    -0.07
    肉
    -0.06
     ethers
    -0.06
     Stored
    -0.06
     campuses
    -0.06
    대로
    -0.06
     FLT
    -0.06
     oste
    -0.06
     undes
    -0.06
     rooms
    -0.06
    POSITIVE LOGITS
     tedy
    0.07
    Figure
    0.07
    BOOL
    0.07
    !"
    0.07
     &#
    0.07
    (nonatomic
    0.06
     "",↵
    0.06
    夢
    0.06
    _proxy
    0.06
     downside
    0.06
    Act Density 0.072%

    No Known Activations