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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Lib
    -0.07
    -commit
    -0.07
    .XPath
    -0.07
    面条
    -0.07
    ırken
    -0.07
     evacuated
    -0.07
     QS
    -0.07
    行业中
    -0.07
     Strategies
    -0.07
     Martin
    -0.07
    POSITIVE LOGITS
    .arg
    0.07
    Fresh
    0.07
    违法
    0.07
    ######↵
    0.07
    ował
    0.07
    uka
    0.07
    롭
    0.07
    oll
    0.06
     favors
    0.06
    ka
    0.06
    Act Density 0.111%

    No Known Activations