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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cottage
    -0.07
    赶
    -0.07
    cron
    -0.07
    σσ
    -0.06
     leng
    -0.06
     게임
    -0.06
     Nou
    -0.06
    효
    -0.06
    sob
    -0.06
    補
    -0.06
    POSITIVE LOGITS
    (admin
    0.07
    体育
    0.07
     literary
    0.07
    .IN
    0.06
     Injection
    0.06
     elusive
    0.06
    ETwitter
    0.06
     intuit
    0.06
     Gl
    0.06
    .columnHeader
    0.06
    Act Density 0.000%

    No Known Activations