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

    Neuronpedia

    INDEX
    Explanations

    print

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     설
    -0.06
     DOT
    -0.06
    ана
    -0.06
     BuzzFeed
    -0.06
     buckets
    -0.06
     ロ
    -0.06
     μα
    -0.06
    提示
    -0.06
     disability
    -0.05
     xr
    -0.05
    POSITIVE LOGITS
     prints
    0.08
     stint
    0.07
    ayız
    0.07
    _NATIVE
    0.07
     keeper
    0.07
    _av
    0.07
    Interested
    0.06
     Latvia
    0.06
    ชม
    0.06
    очного
    0.06
    Act Density 0.009%

    No Known Activations