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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     letz
    -0.06
     Presbyterian
    -0.06
     ward
    -0.06
    руш
    -0.06
     Computes
    -0.06
    reward
    -0.06
    iniz
    -0.06
     believers
    -0.06
     tooltips
    -0.06
    bucks
    -0.06
    POSITIVE LOGITS
    _from
    0.07
     Katherine
    0.07
     altering
    0.07
     beverages
    0.06
     holog
    0.06
     Ahmed
    0.06
     spaghetti
    0.06
     Arrange
    0.06
    .FormattingEnabled
    0.06
     عبدالله
    0.06
    Act Density 0.004%

    No Known Activations