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

    Neuronpedia

    INDEX
    Explanations

    indoor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buck
    -0.10
    setIcon
    -0.09
     Morris
    -0.08
    无疑是
    -0.07
    降低了
    -0.07
    מפק
    -0.07
    氨基
    -0.07
    一点也不
    -0.07
    President
    -0.07
     Amanda
    -0.07
    POSITIVE LOGITS
    饮料
    0.07
    hee
    0.07
     pointers
    0.06
    染
    0.06
    >>>>
    0.06
    PARSE
    0.06
    weets
    0.06
    brightness
    0.06
    鲗
    0.06
    ゥ
    0.06
    Act Density 0.043%

    No Known Activations