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

    Neuronpedia

    INDEX
    Explanations

    Code and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    注åħ¥
    -0.27
    -msg
    -0.26
    ve
    -0.26
    oval
    -0.26
    éĴ
    -0.25
    .att
    -0.24
     sill
    -0.24
    èĢ³
    -0.24
    enne
    -0.24
     trữ
    -0.24
    POSITIVE LOGITS
    ExceptionHandler
    0.29
    -terrorism
    0.26
     quit
    0.26
    ^K
    0.25
     Terrace
    0.25
    quarter
    0.25
    å¦ĤæѤ
    0.24
    quit
    0.24
     quarter
    0.24
    ány
    0.24
    Act Density 0.045%

    No Known Activations