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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     habit
    -0.08
     habits
    -0.08
     Huffington
    -0.08
     Prof
    -0.08
    habit
    -0.08
     رض
    -0.08
     terrace
    -0.08
     Diaries
    -0.08
     PROFITS
    -0.08
     вироб
    -0.08
    POSITIVE LOGITS
     tests
    0.12
     ಪರೀಕ್ಷ
    0.11
     పరీక్ష
    0.11
    判断
    0.10
    判
    0.10
    检测
    0.10
    检
    0.10
     પરી
    0.10
     परीक्षण
    0.10
     പരിശോധന
    0.10
    Act Density 0.012%

    No Known Activations