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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kerry
    -0.07
     análise
    -0.07
     IDb
    -0.07
     exchange
    -0.07
     trực
    -0.07
     DISCLAIMS
    -0.07
     предоставлен
    -0.06
     dwell
    -0.06
     ציבור
    -0.06
    _representation
    -0.06
    POSITIVE LOGITS
     bật
    0.07
    _cv
    0.07
     cohort
    0.07
     Kop
    0.07
    wich
    0.07
     leaderboard
    0.07
    组建
    0.07
    夕
    0.06
     Het
    0.06
    +')
    0.06
    Act Density 0.023%

    No Known Activations