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

    Neuronpedia

    INDEX
    Explanations

    Scraped/diverse internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    所以
    -0.07
    еро
    -0.06
     Leon
    -0.06
     ellipt
    -0.06
     cannon
    -0.06
     Calculate
    -0.06
     phoneNumber
    -0.06
     gli
    -0.06
     farewell
    -0.05
     dengan
    -0.05
    POSITIVE LOGITS
    ्रत
    0.07
     гем
    0.07
     Carlos
    0.06
    IfExists
    0.06
     Beth
    0.06
     Victor
    0.06
    editable
    0.06
     �
    0.06
    (coll
    0.06
    raith
    0.06
    Act Density 0.036%

    No Known Activations