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

    Neuronpedia

    INDEX
    Explanations

    Y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新房
    -0.08
     .$
    -0.07
    富
    -0.07
    .charset
    -0.07
    .Sprite
    -0.07
    .build
    -0.07
    ˔
    -0.07
    -.
    -0.06
     החי
    -0.06
     nông
    -0.06
    POSITIVE LOGITS
     drop
    0.08
     transcend
    0.07
    apatkan
    0.07
    _Begin
    0.07
    宁愿
    0.07
     URLs
    0.07
    Aaron
    0.07
    _published
    0.06
    _monitor
    0.06
    汞
    0.06
    Act Density 0.002%

    No Known Activations