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

    Neuronpedia

    INDEX
    Explanations

    Comparisons and similarities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strr
    -0.07
     seriously
    -0.07
     trunk
    -0.06
    ()}}↵
    -0.06
    _New
    -0.06
     FOR
    -0.06
    pics
    -0.06
    тю
    -0.06
    (answer
    -0.06
     Assurance
    -0.06
    POSITIVE LOGITS
     Savage
    0.07
     impactful
    0.07
     slew
    0.07
    แหน
    0.07
     Lect
    0.06
     Baxter
    0.06
     Perhaps
    0.06
     Magnus
    0.06
    axter
    0.06
    历史
    0.06
    Act Density 0.072%

    No Known Activations