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

    Neuronpedia

    INDEX
    Explanations

    class inheritance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bukkit
    -0.06
     Spokane
    -0.06
    уст
    -0.06
     MainActivity
    -0.06
     adept
    -0.06
     GAP
    -0.06
     karak
    -0.06
    touch
    -0.06
    �数
    -0.06
    dap
    -0.06
    POSITIVE LOGITS
    -European
    0.08
     structures
    0.06
     Serializable
    0.06
     комплекс
    0.06
    ひ
    0.06
    　　 　 　 　 　
    0.06
    gunakan
    0.06
     použí
    0.06
    MER
    0.06
    шается
    0.06
    Act Density 0.002%

    No Known Activations