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

    Neuronpedia

    INDEX
    Explanations

    Scientific interactions and ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cream
    -0.07
     Online
    -0.07
     CC
    -0.07
    空
    -0.07
    赌博
    -0.07
    uede
    -0.07
    _Pin
    -0.07
     creamy
    -0.07
    径
    -0.06
     Aqua
    -0.06
    POSITIVE LOGITS
     stabilize
    0.08
     deployment
    0.07
    移植
    0.07
    始めた
    0.07
    🤖
    0.07
    Insensitive
    0.07
     penetration
    0.07
    itted
    0.07
    _allowed
    0.06
    iving
    0.06
    Act Density 0.023%

    No Known Activations