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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "After
    -0.06
     elegance
    -0.06
    Doug
    -0.06
    _MAY
    -0.06
    urray
    -0.06
    "With
    -0.06
    Very
    -0.06
    eger
    -0.06
     Exercise
    -0.05
    amenti
    -0.05
    POSITIVE LOGITS
     ан
    0.07
     Homes
    0.07
    _clear
    0.07
     manages
    0.06
    _USE
    0.06
     Photos
    0.06
    .Word
    0.06
     EntityState
    0.06
     shareholders
    0.06
     території
    0.06
    Act Density 0.064%

    No Known Activations