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

    Neuronpedia

    INDEX
    Explanations

    genetic algorithm crossover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suburb
    -0.08
    اظ
    -0.07
     cruise
    -0.07
    博物馆
    -0.07
    不适合
    -0.07
    ערים
    -0.07
    畚
    -0.07
    驰
    -0.07
     Cruise
    -0.07
    _CHO
    -0.07
    POSITIVE LOGITS
     moments
    0.07
    vertisement
    0.07
    meeting
    0.07
    �력
    0.07
    時の
    0.06
    🚒
    0.06
    Fixed
    0.06
     engagement
    0.06
    읜
    0.06
    ,last
    0.06
    Act Density 0.011%

    No Known Activations