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

    Neuronpedia

    INDEX
    Explanations

    -based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispersion
    -0.07
     Games
    -0.07
    oleon
    -0.07
     truth
    -0.07
     leaderboard
    -0.07
     Cannon
    -0.06
     counselling
    -0.06
    امه
    -0.06
     Sunset
    -0.06
    λει
    -0.06
    POSITIVE LOGITS
    -derived
    0.07
     QObject
    0.06
    па
    0.06
    ORIZONTAL
    0.06
    ICIAL
    0.06
    -view
    0.06
     أجل
    0.06
    ческих
    0.06
     väl
    0.06
     ofstream
    0.06
    Act Density 0.047%

    No Known Activations