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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     item
    -0.07
    pin
    -0.06
     halk
    -0.06
    	G
    -0.06
     Bro
    -0.06
    guard
    -0.06
    Dam
    -0.06
     Aunt
    -0.06
    laps
    -0.06
    ukkan
    -0.06
    POSITIVE LOGITS
    directories
    0.06
    RESSED
    0.06
     MAR
    0.06
    .GetFiles
    0.06
     kost
    0.06
     ignited
    0.06
     archival
    0.06
     Phy
    0.06
    <style
    0.06
    osing
    0.06
    Act Density 0.005%

    No Known Activations