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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shuffle
    -0.07
     Rs
    -0.07
    _regular
    -0.07
     escorts
    -0.07
     فوت
    -0.07
     Vanderbilt
    -0.07
    COMPLETE
    -0.06
    interpreter
    -0.06
     playwright
    -0.06
    _Part
    -0.06
    POSITIVE LOGITS
     rely
    0.06
    BOOK
    0.06
    _CONTENT
    0.06
    Fortunately
    0.06
     internship
    0.06
    HOW
    0.06
    00
    0.06
    LOB
    0.06
    07
    0.05
     locality
    0.05
    Act Density 0.060%

    No Known Activations